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

    Neuronpedia

    INDEX
    Explanations

    column start of logical rule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.85
     M
    0.79
     I
    0.78
     U
    0.77
     or
    0.76
     V
    0.75
     (
    0.74
     A
    0.72
     W
    0.72
    M
    0.71
    POSITIVE LOGITS
    <unused1839>
    1.17
    Ꮘ
    1.15
     tble
    1.05
     배열
    1.04
     BasicDBObject
    1.04
    tempHeader
    1.03
    𐱅
    1.02
    emptyDict
    1.01
    ẹp
    1.00
    zyła
    1.00
    Act Density 1.205%

    No Known Activations