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

    Neuronpedia

    INDEX
    Explanations

    "is not a" discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аф
    -0.07
     світу
    -0.06
    _stdio
    -0.06
    enha
    -0.06
     tweeted
    -0.06
    ク
    -0.06
     earnings
    -0.06
    *=
    -0.06
    ascending
    -0.06
    Private
    -0.06
    POSITIVE LOGITS
    /how
    0.07
    .springframework
    0.06
    bral
    0.06
    unic
    0.06
    Ng
    0.06
    بیر
    0.06
    /n
    0.06
    .series
    0.06
     سلام
    0.06
    	Json
    0.05
    Act Density 0.045%

    No Known Activations