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

    Neuronpedia

    INDEX
    Explanations

    products, map pieces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نة
    0.48
    使い方
    0.46
    お手
    0.45
    شي
    0.45
     autorización
    0.45
    number
    0.44
    ум
    0.43
     admiration
    0.43
    اح
    0.41
     éclat
    0.41
    POSITIVE LOGITS
     Abol
    0.46
     Oli
    0.46
     Aryan
    0.45
    രുത്
    0.44
    BackButton
    0.44
    rpm
    0.43
     Kakkar
    0.42
     Poon
    0.42
     Theology
    0.42
    KAM
    0.42
    Act Density 0.001%

    No Known Activations