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

    Neuronpedia

    INDEX
    Explanations

    dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sacred
    -0.07
    Loading
    -0.06
     liability
    -0.06
     Poetry
    -0.06
    7
    -0.06
    tk
    -0.06
     Wilson
    -0.06
    Layout
    -0.06
    Grammar
    -0.06
     Mix
    -0.06
    POSITIVE LOGITS
    िच
    0.08
    ]+$
    0.07
    ροφορ
    0.06
     火
    0.06
    (expr
    0.06
    ，如
    0.06
    ังไม
    0.06
     almacen
    0.06
    reo
    0.06
    rå
    0.06
    Act Density 0.002%

    No Known Activations