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

    Neuronpedia

    INDEX
    Explanations

    say "["

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    、、、
    0.85
    ',(
    0.83
    .......
    0.82
    }}{\
    0.82
    }}(
    0.81
    ---------
    0.79
    〃
    0.78
    0.77
    .........
    0.76
    }}(\
    0.76
    POSITIVE LOGITS
     [
    4.49
    [
    3.81
     $[
    3.04
     \[
    2.93
     [_
    2.64
     [$
    2.62
     [-
    2.61
    ［
    2.60
    [-
    2.50
    -[
    2.48
    Act Density 0.276%

    No Known Activations