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

    Neuronpedia

    INDEX
    Explanations

    pandas read file parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UJ
    0.40
    ujan
    0.38
    TEM
    0.37
     dares
    0.37
    ｲ
    0.37
    旅
    0.36
    とい
    0.36
     లే
    0.36
    QUI
    0.36
     एसिड
    0.36
    POSITIVE LOGITS
     πάν
    0.41
     Ads
    0.40
    çç
    0.38
     actions
    0.38
    index
    0.37
     frivol
    0.37
    蒽
    0.37
    reatment
    0.35
    ώς
    0.35
     provocative
    0.35
    Act Density 0.001%

    No Known Activations