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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     competency
    -0.06
    ّم
    -0.06
    lection
    -0.06
     like
    -0.06
     apocalypse
    -0.06
     geçir
    -0.06
     competition
    -0.06
    .setInt
    -0.06
     чин
    -0.06
    Introduction
    -0.06
    POSITIVE LOGITS
    (Function
    0.07
     �
    0.06
     nr
    0.06
    Twenty
    0.06
     bland
    0.06
     roleName
    0.06
    (O
    0.06
     kolem
    0.06
    ử
    0.06
     ores
    0.06
    Act Density 0.022%

    No Known Activations