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

    Neuronpedia

    INDEX
    Explanations

    share

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    seek
    -0.08
     Nin
    -0.07
    sex
    -0.07
     nomination
    -0.07
    chem
    -0.07
    lut
    -0.07
     amus
    -0.07
    .seek
    -0.07
    (parsed
    -0.07
    seq
    -0.07
    POSITIVE LOGITS
     nhau
    0.09
     Legs
    0.08
     территории
    0.08
     condiv
    0.08
    壁
    0.08
     legs
    0.08
     highway
    0.08
     ortak
    0.08
     latter
    0.08
    ービス
    0.08
    Act Density 0.008%

    No Known Activations