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

    Neuronpedia

    INDEX
    Explanations

    Language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nud
    -0.06
    istik
    -0.06
    バス
    -0.06
    "a
    -0.06
    touch
    -0.06
    're
    -0.06
     entail
    -0.06
     proc
    -0.05
    _ud
    -0.05
    ığı
    -0.05
    POSITIVE LOGITS
    May
    0.07
    adesh
    0.07
    таж
    0.07
     Ελλά
    0.07
    /div
    0.07
     rises
    0.07
    quisition
    0.06
     Breaking
    0.06
     doğru
    0.06
    /min
    0.06
    Act Density 0.185%

    No Known Activations