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

    Neuronpedia

    INDEX
    Explanations

    changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     αξ
    -0.07
    gunakan
    -0.07
     explain
    -0.06
     Proxy
    -0.06
    тех
    -0.06
    ़
    -0.06
     Hardcover
    -0.06
    ัคร
    -0.06
    Communic
    -0.06
    rollback
    -0.06
    POSITIVE LOGITS
     mes
    0.07
     dominant
    0.07
     detalles
    0.07
     adjustments
    0.07
     thoughts
    0.07
     davranış
    0.06
     Charl
    0.06
    _STEP
    0.06
     Studies
    0.06
     подс
    0.06
    Act Density 0.029%

    No Known Activations