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

    Neuronpedia

    INDEX
    Explanations

    fields of study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muttered
    -0.06
    енням
    -0.06
    нат
    -0.06
    ↵↵↵↵↵
    -0.06
     хто
    -0.06
     ankles
    -0.06
     Cait
    -0.06
    aket
    -0.06
    ниця
    -0.06
    fal
    -0.06
    POSITIVE LOGITS
     environmental
    0.07
     GF
    0.07
    setVisible
    0.06
     ");
    0.06
    руж
    0.06
     Law
    0.06
     Cycling
    0.06
    combined
    0.06
     yard
    0.06
     geological
    0.06
    Act Density 0.043%

    No Known Activations