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

    Neuronpedia

    INDEX
    Explanations

    terms related to individual identity and characteristics

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

    individual characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.76
     '\\;'
    -0.75
    tanleria
    -0.71
    DockStyle
    -0.68
    Hentet
    -0.67
    PreInfinity
    -0.67
    pecabe
    -0.66
    ocardio
    -0.66
     AssemblyCulture
    -0.66
    genodigd
    -0.66
    POSITIVE LOGITS
    ,
    0.47
     extra
    0.46
     individual
    0.41
    .
    0.40
     in
    0.39
    :
    0.39
     dual
    0.38
     a
    0.36
     protest
    0.36
    lső
    0.36
    Act Density 0.158%

    No Known Activations