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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cigar
    -0.07
     Himself
    -0.07
     accomplishment
    -0.07
    .Notify
    -0.07
     участ
    -0.07
    Professor
    -0.07
     Benef
    -0.07
     broadcasting
    -0.06
    Recent
    -0.06
     cigars
    -0.06
    POSITIVE LOGITS
     knives
    0.07
    ność
    0.07
    織
    0.06
    ничес
    0.06
    ệ
    0.06
     její
    0.06
     enables
    0.06
    villa
    0.06
    ولو
    0.06
    hue
    0.06
    Act Density 0.016%

    No Known Activations