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

    Neuronpedia

    INDEX
    Explanations

    artist/author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /tests
    -0.07
     blat
    -0.06
    -Day
    -0.06
    -transfer
    -0.06
    不足
    -0.06
     س
    -0.06
    疗
    -0.06
    ซ
    -0.06
    Success
    -0.06
    ritable
    -0.06
    POSITIVE LOGITS
     有
    0.07
    .sale
    0.07
    けど
    0.07
    .work
    0.06
     впол
    0.06
    recogn
    0.06
     még
    0.06
     ав
    0.06
     позвол
    0.06
    也有
    0.06
    Act Density 0.020%

    No Known Activations