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

    Neuronpedia

    INDEX
    Explanations

    greetings to many

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SAC
    0.54
    зю
    0.54
    🇶
    0.51
     CMA
    0.50
     лиш
    0.50
    மணி
    0.49
    jších
    0.48
    ệng
    0.48
     CFL
    0.48
    ீர்கள்
    0.47
    POSITIVE LOGITS
    L
    0.68
    T
    0.66
    st
    0.65
    H
    0.64
    B
    0.63
    ro
    0.63
    ler
    0.61
    (
    0.61
    de
    0.60
    （
    0.60
    Act Density 0.004%

    No Known Activations