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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shrine
    -0.07
     Cold
    -0.07
     vulgar
    -0.06
     GM
    -0.06
     شم
    -0.06
    ofil
    -0.06
    onds
    -0.06
    文献
    -0.06
    _none
    -0.06
     لینک
    -0.06
    POSITIVE LOGITS
    (:,:,
    0.07
    ữu
    0.07
    ServletResponse
    0.06
     количества
    0.06
     depreci
    0.06
    补
    0.06
    inte
    0.06
    istency
    0.06
    _partition
    0.06
    .Sql
    0.06
    Act Density 0.002%

    No Known Activations