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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aphyl
    -0.08
     singleton
    -0.08
    _drive
    -0.07
    වු
    -0.07
    ăn
    -0.07
    Drive
    -0.07
     نف
    -0.07
    singleton
    -0.07
    šanas
    -0.07
    مكان
    -0.07
    POSITIVE LOGITS
     हिस्स
    0.12
     أجزاء
    0.11
    ส่วน
    0.10
     parts
    0.10
     частей
    0.10
    fass
    0.09
     हिस्सा
    0.09
     části
    0.09
    stück
    0.09
    portion
    0.09
    Act Density 0.143%

    No Known Activations