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

    Neuronpedia

    INDEX
    Explanations

    raw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Generally
    -0.07
     Erdoğan
    -0.07
    Sadly
    -0.06
     ゝ
    -0.06
     Releases
    -0.06
    _rad
    -0.06
     hlav
    -0.06
     üretim
    -0.06
    nick
    -0.06
    広
    -0.06
    POSITIVE LOGITS
    /csv
    0.07
     đòi
    0.06
    enzyme
    0.06
     обличчя
    0.06
    #================================================================
    0.06
    Interstitial
    0.06
    ,,
    0.06
    になって
    0.06
    engine
    0.05
    req
    0.05
    Act Density 0.027%

    No Known Activations