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

    Neuronpedia

    INDEX
    Explanations

    say 0 or 1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בן
    -0.08
    팻
    -0.08
    pron
    -0.07
    apixel
    -0.07
    קיימת
    -0.07
    בעל
    -0.07
    אין
    -0.07
    /respond
    -0.07
    ユー
    -0.07
    뀝
    -0.06
    POSITIVE LOGITS
    .window
    0.07
     holdings
    0.06
    ата
    0.06
    	seq
    0.06
    .shift
    0.06
    ﯞ
    0.06
    zy
    0.06
    obook
    0.06
    дж
    0.06
    -commerce
    0.06
    Act Density 0.091%

    No Known Activations