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

    Neuronpedia

    INDEX
    Explanations

    ballots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ago
    -0.06
    ，每
    -0.06
     sẽ
    -0.06
    contro
    -0.06
    ıc
    -0.06
    ्रमण
    -0.06
     Sandra
    -0.06
    Không
    -0.05
    ety
    -0.05
     setEmail
    -0.05
    POSITIVE LOGITS
    vit
    0.07
    :animated
    0.07
    >E
    0.07
    >F
    0.07
     klass
    0.07
     SHIFT
    0.06
    습
    0.06
    goals
    0.06
    979
    0.06
    аз
    0.06
    Act Density 0.084%

    No Known Activations