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

    Neuronpedia

    INDEX
    Explanations

    default cases or fallback conditions in programming logic

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

    Code or mathematical conditions

    np_acts-logits-general · gemini-2.0-flash

    code and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CROSSTALK
    -0.64
     Révolution
    -0.58
     Polda
    -0.55
     フリー
    -0.53
     Hannover
    -0.52
    Bibliografie
    -0.52
    Naissance
    -0.52
    ərbaycan
    -0.52
     Schenk
    -0.51
    saraba
    -0.51
    POSITIVE LOGITS
    enumi
    1.16
    enumii
    0.90
    AndEndTag
    0.81
    AccessorTable
    0.78
    InputBorder
    0.76
    __':
    0.72
     виправивши
    0.72
    __":
    0.71
    __':
    0.70
    __":
    0.64
    Act Density 0.006%

    No Known Activations