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

    Neuronpedia

    INDEX
    Explanations

    town descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     руки
    -0.07
    ока
    -0.06
     будуть
    -0.06
    ору
    -0.06
    iž
    -0.06
    우
    -0.06
    FixedSize
    -0.06
    supply
    -0.06
    ensely
    -0.06
      ↵↵
    -0.06
    POSITIVE LOGITS
     aj
    0.07
     parlament
    0.07
    Telephone
    0.07
     durable
    0.06
    =G
    0.06
    .admin
    0.06
     Sınıf
    0.06
    .message
    0.06
    -picker
    0.06
    executable
    0.06
    Act Density 0.021%

    No Known Activations