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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     presented
    -0.06
    -project
    -0.06
     nabízí
    -0.06
    ař
    -0.06
    ,l
    -0.06
    andalone
    -0.06
     getConnection
    -0.06
    BagConstraints
    -0.06
    pthread
    -0.06
     hvor
    -0.06
    POSITIVE LOGITS
     행동
    0.07
     výro
    0.07
     rockets
    0.06
    otty
    0.06
    意见
    0.06
     shots
    0.06
     khổ
    0.06
     soci
    0.06
    аша
    0.06
     그래서
    0.06
    Act Density 0.000%

    No Known Activations