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

    Neuronpedia

    INDEX
    Explanations

    AI assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Моск
    0.43
    <unused2130>
    0.43
    oci
    0.42
     irrepar
    0.42
    Barr
    0.39
     affiliates
    0.38
    pliance
    0.38
    posals
    0.37
    िलायंस
    0.37
    andex
    0.37
    POSITIVE LOGITS
     خوان
    0.45
     adimensional
    0.44
     ہوتی
    0.44
     نمونه
    0.44
     হবেনা
    0.44
     تصمیم
    0.44
     ہ
    0.43
    Longueur
    0.43
     fler
    0.43
    Retour
    0.43
    Act Density 0.007%

    No Known Activations