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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opportun
    -0.08
    acco
    -0.08
     the
    -0.07
     signalling
    -0.07
     Schneider
    -0.07
     Nak
    -0.07
     Nast
    -0.07
     accommod
    -0.07
     signaling
    -0.07
    lery
    -0.07
    POSITIVE LOGITS
     鹤
    0.09
     coluna
    0.09
     besteed
    0.09
     writer
    0.09
     描
    0.09
     hlay
    0.09
     undertøy
    0.09
    usband
    0.08
     鄂
    0.08
     descripción
    0.08
    Act Density 0.001%

    No Known Activations