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

    Neuronpedia

    INDEX
    Explanations

    used for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    व्य
    1.32
     हस्ताक्षर
    1.19
     Schritte
    1.15
    해
    1.13
    ㅁ
    1.09
    Brass
    1.07
     potrivit
    1.03
     heer
    1.03
    ']])
    1.03
     moe
    1.03
    POSITIVE LOGITS
    ان
    1.42
     whopping
    1.20
     muka
    1.18
     staggering
    1.17
    piece
    1.16
    cę
    1.13
     excelled
    1.12
     enduring
    1.11
    neux
    1.10
    ਿਕ
    1.10
    Act Density 0.000%

    No Known Activations