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

    Neuronpedia

    INDEX
    Explanations

    references to global parameters or variables in code

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

    globalglobal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.61
    ">//
    -0.54
    makeText
    -0.54
    enumi
    -0.53
     mergeFrom
    -0.52
    enumii
    -0.50
    uxxxx
    -0.49
    httphttps
    -0.49
    pushFollow
    -0.45
    mittee
    -0.44
    POSITIVE LOGITS
    global
    2.00
    GLOBAL
    1.06
     global
    0.91
    Global
    0.88
     GLOBAL
    0.87
     Global
    0.76
    globals
    0.74
    lobal
    0.69
     globales
    0.67
    glo
    0.64
    Act Density 0.003%

    No Known Activations