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

    Neuronpedia

    INDEX
    Explanations

    Attribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strings
    -0.07
    _DOC
    -0.07
     Tele
    -0.07
    缩水
    -0.07
    magic
    -0.07
    visibility
    -0.07
    _map
    -0.06
    �
    -0.06
     cosine
    -0.06
     Judge
    -0.06
    POSITIVE LOGITS
     advised
    0.07
    avenous
    0.07
     müzik
    0.06
     patië
    0.06
    治病
    0.06
     atheist
    0.06
     клуб
    0.06
    .Age
    0.06
    路
    0.06
    Kat
    0.06
    Act Density 0.001%

    No Known Activations