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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .encoder
    -0.07
    .Geometry
    -0.07
    _PHYS
    -0.06
     شیر
    -0.06
    ighbor
    -0.06
     torpedo
    -0.06
     oby
    -0.06
     Oy
    -0.06
    aly
    -0.06
    ορειο
    -0.06
    POSITIVE LOGITS
    ليات
    0.07
     nameLabel
    0.07
     Anglic
    0.06
    "title
    0.06
     Catalan
    0.06
    ディ
    0.06
    อน
    0.06
    alpha
    0.06
    สถานท
    0.06
    chants
    0.06
    Act Density 0.037%

    No Known Activations