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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breaches
    -0.07
     más
    -0.07
     OK
    -0.07
     slideshow
    -0.06
    and
    -0.06
    Recorder
    -0.06
    _front
    -0.06
    almart
    -0.06
    .trade
    -0.06
     holes
    -0.06
    POSITIVE LOGITS
    perl
    0.07
     перева
    0.07
    éf
    0.06
    대의
    0.06
     ор
    0.06
     println
    0.06
     بالإ
    0.06
    OPSIS
    0.06
    .isFile
    0.06
     lệnh
    0.06
    Act Density 0.019%

    No Known Activations