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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Strategy
    -0.09
     strategy
    -0.07
     Replies
    -0.06
     submissions
    -0.06
    _final
    -0.06
    jed
    -0.06
    kol
    -0.06
     Wenger
    -0.06
     Historic
    -0.06
    事情
    -0.06
    POSITIVE LOGITS
    ับส
    0.07
    .jsx
    0.07
    /is
    0.07
    られている
    0.07
    .TestCheck
    0.06
    retorno
    0.06
     dziewcz
    0.06
    ilig
    0.06
     نمای
    0.06
    μένου
    0.06
    Act Density 0.051%

    No Known Activations