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

    Neuronpedia

    INDEX
    Explanations

    Programming context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fuera
    -0.07
     Baz
    -0.07
     Hebrew
    -0.06
     chol
    -0.06
     thigh
    -0.06
     Pais
    -0.06
    .likes
    -0.06
     Aly
    -0.06
    _half
    -0.06
     Ip
    -0.06
    POSITIVE LOGITS
     medications
    0.06
    čný
    0.06
    _WITH
    0.06
     visto
    0.06
     republiky
    0.06
    .try
    0.06
     باشگاه
    0.06
    ocommerce
    0.06
    德
    0.06
     Cul
    0.06
    Act Density 0.043%

    No Known Activations