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

    Neuronpedia

    INDEX
    Explanations

    references to personal beliefs and identities

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

    possessions and associations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     automated
    -0.71
     automatic
    -0.67
    automatic
    -0.63
     automat
    -0.62
     automatically
    -0.59
     automate
    -0.59
     автомати
    -0.59
     Automated
    -0.56
    Automatic
    -0.55
    automated
    -0.55
    POSITIVE LOGITS
    contentLoaded
    0.63
     Italijanski
    0.62
     Италијани
    0.59
     iprot
    0.59
    writeField
    0.57
    CloseOperation
    0.56
    лтемелер
    0.56
    InitVars
    0.55
    RTEX
    0.55
    transQ
    0.55
    Act Density 0.083%

    No Known Activations