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

    Neuronpedia

    INDEX
    Explanations

    pin connectors and circuits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    茎
    -0.07
    _PRIMARY
    -0.07
     vertex
    -0.07
    pheric
    -0.07
     DELETE
    -0.07
    穿搭
    -0.07
    瓷
    -0.06
     correo
    -0.06
     Γ
    -0.06
    清洁能源
    -0.06
    POSITIVE LOGITS
     scares
    0.08
    +[
    0.07
    .loadtxt
    0.07
     Holy
    0.06
     whats
    0.06
    路演
    0.06
    alyze
    0.06
    游戏当中
    0.06
    (Global
    0.06
     safest
    0.06
    Act Density 0.025%

    No Known Activations