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

    Neuronpedia

    INDEX
    Explanations

    table structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.81
    ↵↵
    0.76
    es
    0.74
     some
    0.73
     directly
    0.66
    />
    0.66
    \
    0.66
     in
    0.65
     ecosystem
    0.64
     [
    0.60
    POSITIVE LOGITS
     तालिका
    1.17
    <tr>
    1.15
    룺
    1.12
    TableRow
    1.12
    emptyDict
    1.11
    땃
    1.10
    MaxIntensity
    1.08
     -------------
    1.08
    <unused372>
    1.08
     -----------
    1.07
    Act Density 0.137%

    No Known Activations