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

    Neuronpedia

    INDEX
    Explanations

    own

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SuppressLint
    -0.07
     Вас
    -0.07
    埯
    -0.07
     bother
    -0.06
     한번
    -0.06
     seasoned
    -0.06
     evolve
    -0.06
    xEE
    -0.06
     packed
    -0.06
     gradu
    -0.06
    POSITIVE LOGITS
    강
    0.07
    outcome
    0.07
    _eng
    0.07
    粉色
    0.07
    рут
    0.07
    不錯
    0.07
    (ag
    0.06
     Arabian
    0.06
    0.06
    出自
    0.06
    Act Density 0.003%

    No Known Activations