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

    Neuronpedia

    INDEX
    Explanations

    ize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (schedule
    -0.07
     requester
    -0.07
     กำ
    -0.06
     courier
    -0.06
     dangerous
    -0.06
    _generator
    -0.06
    Ki
    -0.06
    Seven
    -0.06
     swallowed
    -0.06
     hospodář
    -0.06
    POSITIVE LOGITS
    \Form
    0.07
    ilestone
    0.06
     чемпіон
    0.06
    dea
    0.06
    ivel
    0.06
     criticism
    0.06
     víde
    0.06
    .Annotation
    0.06
    couz
    0.06
     환산
    0.06
    Act Density 0.026%

    No Known Activations