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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PRETTY
    -0.06
     Minor
    -0.06
    everything
    -0.06
     shortly
    -0.06
    еріга
    -0.06
    _prefs
    -0.06
     Film
    -0.06
    Bah
    -0.06
    失败
    -0.06
    สาห
    -0.06
    POSITIVE LOGITS
    riends
    0.07
    ::*
    0.06
    guid
    0.06
    rial
    0.06
    екту
    0.06
    /public
    0.06
    .azure
    0.06
    forums
    0.06
     histograms
    0.06
     donor
    0.06
    Act Density 0.041%

    No Known Activations