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

    Neuronpedia

    INDEX
    Explanations

    comment explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     can
    1.93
     are
    1.60
     it
    1.13
     an
    1.09
     in
    1.09
     larvae
    1.08
     plasmid
    1.05
     alat
    1.05
    ।
    1.05
     juga
    1.05
    POSITIVE LOGITS
    is
    1.63
    at
    1.55
    ти
    1.24
     for
    1.18
    rů
    1.16
    el
    1.14
    ৬
    1.14
    ла
    1.13
    ون
    1.13
    اتي
    1.12
    Act Density 0.012%

    No Known Activations