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

    Neuronpedia

    INDEX
    Explanations

    proposed followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     L
    1.02
     S
    0.88
     J
    0.88
     T
    0.86
     V
    0.84
     W
    0.84
     C
    0.82
     M
    0.81
     B
    0.81
     H
    0.80
    POSITIVE LOGITS
     proposed
    0.69
    Proposed
    0.62
    ित
    0.61
    enan
    0.61
    itively
    0.59
    asen
    0.58
    proposed
    0.56
     to
    0.53
    ena
    0.53
    ेक्ट
    0.53
    Act Density 0.003%

    No Known Activations