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

    Neuronpedia

    INDEX
    Explanations

    specific labels or variables associated with experimental data

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

    figure labels (F, H)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OnInit
    -0.49
    ̈́
    -0.48
    AutoScale
    -0.46
    Burn
    -0.45
     kyllä
    -0.44
     olvas
    -0.44
    -0.44
    lineHeight
    -0.43
     enää
    -0.43
     cerimonia
    -0.43
    POSITIVE LOGITS
     Numerade
    0.46
    UnknownFieldSet
    0.36
    setCellValue
    0.33
     alternativ
    0.31
     assignment
    0.31
    GTCX
    0.31
    جغرافيا
    0.31
    Abitanti
    0.31
    SharedDtor
    0.30
     informée
    0.29
    Act Density 0.380%

    No Known Activations