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

    Neuronpedia

    INDEX
    Explanations

    blocks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _students
    -0.06
     annotate
    -0.06
    нів
    -0.06
    平台
    -0.06
     captcha
    -0.06
     препара
    -0.06
     saldırı
    -0.06
    、高
    -0.06
     Huntington
    -0.06
    аран
    -0.06
    POSITIVE LOGITS
     Genetic
    0.07
     Richard
    0.07
     eligibility
    0.07
     rooted
    0.06
    PUR
    0.06
     Candid
    0.06
    Nick
    0.06
    -owned
    0.06
    229
    0.06
    "If
    0.06
    Act Density 0.016%

    No Known Activations