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

    Neuronpedia

    INDEX
    Explanations

    0 followed by 1s and 2s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whanne
    0.66
     \%$,
    0.65
     detergents
    0.64
     concomit
    0.63
     relatives
    0.60
     quorum
    0.59
     distributions
    0.57
     nostalg
    0.57
     pauses
    0.56
     deterior
    0.55
    POSITIVE LOGITS
    A
    0.83
    P
    0.78
    V
    0.78
    T
    0.73
    W
    0.70
    D
    0.69
    G
    0.68
    S
    0.67
    L
    0.66
    I
    0.65
    Act Density 0.476%

    No Known Activations