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

    Neuronpedia

    INDEX
    Explanations

    said that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     what
    -1.78
    鵟
    -1.77
    When
    -1.71
    Además
    -1.68
    Jika
    -1.66
    Они
    -1.66
    Также
    -1.65
     When
    -1.59
     дуже
    -1.58
     also
    -1.57
    POSITIVE LOGITS
    ↵↵
    1.93
     “
    1.57
     is
    1.48
     announces
    1.37
     be
    1.33
     sum
    1.33
    </u>
    1.32
     on
    1.31
    hose
    1.26
    = 
    1.26
    Act Density 0.030%

    No Known Activations