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

    Neuronpedia

    INDEX
    Explanations

    explains/enumerates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    1.45
    ,
    1.39
    (
    1.17
    .
    1.13
    "/"
    1.04
    ।
    0.95
    Entonces
    0.93
    ,//
    0.92
    。
    0.91
    （
    0.90
    POSITIVE LOGITS
     while
    1.71
     since
    1.63
     despite
    1.59
     when
    1.56
     during
    1.55
     protože
    1.55
     although
    1.55
     if
    1.48
     wenn
    1.48
     because
    1.48
    Act Density 0.305%

    No Known Activations