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

    Neuronpedia

    INDEX
    Explanations

    .body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    руют
    -0.07
     треба
    -0.06
     کرده
    -0.06
     compartir
    -0.06
    (percent
    -0.06
     earthquake
    -0.06
    _representation
    -0.06
    Active
    -0.06
    なんだ
    -0.06
     erhalten
    -0.06
    POSITIVE LOGITS
     imb
    0.07
     Sting
    0.06
    -doc
    0.06
    _CRYPTO
    0.06
    ेष
    0.06
    도
    0.06
    ATA
    0.06
     sund
    0.06
     wish
    0.06
    اي
    0.06
    Act Density 0.002%

    No Known Activations