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

    Neuronpedia

    INDEX
    Explanations

    terms related to functionality and usability in software or data processing contexts

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

    known as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aholisi
    -0.63
    msgSender
    -0.49
    expandindo
    -0.47
     defaultstate
    -0.46
    AutoField
    -0.44
     jsPsych
    -0.43
    rrggbb
    -0.39
     Roskov
    -0.39
    contentLoaded
    -0.37
    ronpa
    -0.37
    POSITIVE LOGITS
     jüdis
    0.49
    Correct
    0.46
    intele
    0.46
    fören
    0.45
     parseFrom
    0.44
    neither
    0.44
    pecabe
    0.43
    ┼
    0.42
    indi
    0.42
     Gilmour
    0.42
    Act Density 0.098%

    No Known Activations