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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    투
    -0.07
    -kit
    -0.06
    231
    -0.06
     管
    -0.06
     Across
    -0.06
    sum
    -0.06
    models
    -0.06
    跨
    -0.06
     wash
    -0.06
     mekan
    -0.06
    POSITIVE LOGITS
    ディース
    0.07
     годы
    0.06
    _CUDA
    0.06
     ech
    0.06
    iện
    0.06
     ub
    0.06
    divide
    0.06
    RIPTION
    0.06
    yling
    0.06
     Phương
    0.06
    Act Density 0.020%

    No Known Activations