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

    Neuronpedia

    INDEX
    Explanations

    cutting off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ындағы
    -0.08
    Portugu
    -0.07
     подпис
    -0.07
     Macintosh
    -0.07
     Processing
    -0.07
    иг
    -0.07
     fscanf
    -0.07
    　
    -0.07
     Tensor
    -0.07
    (width
    -0.07
    POSITIVE LOGITS
     abruptly
    0.12
     abrupt
    0.10
     interrom
    0.10
     vigorous
    0.10
    Frm
    0.09
    伏
    0.09
     interrupted
    0.09
    -stop
    0.08
     shy
    0.08
    TERM
    0.08
    Act Density 0.007%

    No Known Activations