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

    Neuronpedia

    INDEX
    Explanations

    hay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TextUtils
    -0.07
    rani
    -0.07
    menin
    -0.07
     अध
    -0.07
    -digit
    -0.06
    fv
    -0.06
     Louise
    -0.06
     Fra
    -0.06
     malign
    -0.06
     banquet
    -0.06
    POSITIVE LOGITS
     شبکه
    0.06
    (conf
    0.06
    CP
    0.06
     Место
    0.06
     Род
    0.06
    sq
    0.06
    До
    0.06
     DHS
    0.05
    弾
    0.05
     chiến
    0.05
    Act Density 0.025%

    No Known Activations