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

    Neuronpedia

    INDEX
    Explanations

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    มงคล
    -0.08
     eo
    -0.08
    .jet
    -0.07
    adors
    -0.07
    ;!
    -0.07
    itorio
    -0.07
    鬧
    -0.07
     onSubmit
    -0.07
    >?
    -0.07
    菔
    -0.07
    POSITIVE LOGITS
    -elect
    0.07
    WER
    0.07
    -boy
    0.07
     cm
    0.06
    —or
    0.06
    izing
    0.06
    _FR
    0.06
    تحرير
    0.06
    .UR
    0.06
     confirming
    0.06
    Act Density 0.005%

    No Known Activations