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

    Neuronpedia

    INDEX
    Explanations

    math notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ass
    -0.08
     vindo
    -0.08
     אב
    -0.08
     مند
    -0.08
     والأ
    -0.08
    ني
    -0.07
     acess
    -0.07
     دا
    -0.07
     گے
    -0.07
    一般
    -0.07
    POSITIVE LOGITS
    條
    0.08
    (condition
    0.08
     koş
    0.08
    _conditions
    0.08
    Conversation
    0.08
    exists
    0.08
    (math
    0.08
    (adj
    0.08
    0.08
    -condition
    0.08
    Act Density 0.003%
    No Known Activations