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

    Neuronpedia

    INDEX
    Explanations

    Normal and natural things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ro
    -0.07
    ετ
    -0.06
     swallow
    -0.06
     Blow
    -0.06
    ovém
    -0.06
    ेश
    -0.06
     YORK
    -0.06
    .Class
    -0.06
     IGN
    -0.06
    801
    -0.06
    POSITIVE LOGITS
     ").
    0.07
    _SZ
    0.06
     CHARACTER
    0.06
    star
    0.06
    ayı
    0.06
     irq
    0.06
    yster
    0.06
     dissolve
    0.06
     перел
    0.06
    problem
    0.06
    Act Density 0.024%

    No Known Activations