Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and error messages related to programming or software issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    incorrect or erroneous results

    np_acts-logits-general · gemini-2.0-flash

    incorrect results or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.72
    celotti
    -0.54
    ReusableCell
    -0.54
     MainAxisSize
    -0.52
    ImageContext
    -0.48
    MigrationBuilder
    -0.48
    basicConfig
    -0.47
     tinggal
    -0.44
    inquirer
    -0.44
     externi
    -0.44
    POSITIVE LOGITS
     incorrectly
    1.06
     erroneously
    1.04
     spurious
    0.95
     unintended
    0.94
     bug
    0.93
     wrongly
    0.90
     erroneous
    0.90
    bug
    0.86
     unintentionally
    0.85
     incorrect
    0.85
    Act Density 0.901%

    No Known Activations