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

    Neuronpedia

    INDEX
    Explanations

    Large numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RNA
    -0.08
     Reduction
    -0.07
     retaliation
    -0.07
    xiety
    -0.06
    rypt
    -0.06
     stead
    -0.06
    플
    -0.06
     จาก
    -0.06
    .games
    -0.06
     francaise
    -0.06
    POSITIVE LOGITS
    ream
    0.06
    .tagName
    0.06
    Too
    0.06
    <Field
    0.06
    insula
    0.06
    Quote
    0.06
    إن
    0.06
     gmail
    0.06
     Slider
    0.06
    Ар
    0.06
    Act Density 0.009%

    No Known Activations