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

    Neuronpedia

    INDEX
    Explanations

    ukh followed by ovich

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.98
    นัก
    0.88
    inin
    0.85
    सामान्यीकृत
    0.84
    on
    0.83
    していました
    0.83
    uhi
    0.82
    icznej
    0.82
    しみ
    0.80
    ือ
    0.79
    POSITIVE LOGITS
    2
    1.06
     or
    0.99
     be
    0.98
     on
    0.96
    I
    0.94
     and
    0.94
    at
    0.91
     are
    0.91
     $
    0.89
     a
    0.88
    Act Density 0.000%

    No Known Activations