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

    Neuronpedia

    INDEX
    Explanations

    size number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اشاره
    -0.07
     お
    -0.07
     HOLDERS
    -0.06
     humility
    -0.06
    _auth
    -0.06
    Temporal
    -0.06
     stata
    -0.06
     seguridad
    -0.06
    .plot
    -0.06
     Feng
    -0.06
    POSITIVE LOGITS
     scri
    0.06
     disposed
    0.06
    (cs
    0.06
     wrapping
    0.06
    <p
    0.06
    (expect
    0.06
    (Table
    0.06
    ."+
    0.06
     Spring
    0.06
     paragraphs
    0.06
    Act Density 0.009%

    No Known Activations