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

    Neuronpedia

    INDEX
    Explanations

    truncated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     стих
    -0.07
    athons
    -0.07
    assa
    -0.07
     متخصص
    -0.07
     bullet
    -0.07
    ieno
    -0.07
     विश्व
    -0.07
     जाए
    -0.07
     вра
    -0.07
    فاع
    -0.07
    POSITIVE LOGITS
     sliced
    0.09
    _ABORT
    0.09
    Abort
    0.09
     trunc
    0.08
    부분
    0.08
    填
    0.08
     Abort
    0.08
     cropping
    0.08
     Dop
    0.08
     квартира
    0.08
    Act Density 0.005%

    No Known Activations