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

    Neuronpedia

    INDEX
    Explanations

    file paths and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mixing
    -0.07
    ации
    -0.07
     WINDOWS
    -0.07
     configurations
    -0.06
    ящ
    -0.06
    сим
    -0.06
    μένο
    -0.06
    (states
    -0.06
     Soy
    -0.06
     house
    -0.06
    POSITIVE LOGITS
     چنین
    0.06
    _inactive
    0.06
    %i
    0.06
    .setError
    0.06
    ollow
    0.06
    :Set
    0.06
    Timeline
    0.06
    ısıt
    0.06
    تبه
    0.06
    _tb
    0.06
    Act Density 0.000%

    No Known Activations