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

    Neuronpedia

    INDEX
    Explanations

    sections of text that discuss categories or classifications

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

    Preceding a category or reference

    np_acts-logits-general · gemini-2.0-flash

    section headers and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.79
    -
    -0.79
    :
    -0.78
     
    -0.76
    .
    -0.72
    ...
    -0.71
     -
    -0.69
    a
    -0.68
    ;
    -0.66
    /
    -0.65
    POSITIVE LOGITS
     itſelf
    1.67
     myſelf
    1.60
     bezeichneter
    1.47
     Efq
    1.38
    IUrlHelper
    1.38
     themſelves
    1.35
    expandindo
    1.33
    ^(@)
    1.32
     Forumite
    1.31
    ſelves
    1.30
    Act Density 0.084%

    No Known Activations