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

    Neuronpedia

    INDEX
    Explanations

    go a long way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     architecture
    0.73
    ithub
    0.65
     Bah
    0.65
     Nouveau
    0.64
    usp
    0.63
     architectures
    0.62
     بخ
    0.62
     නව
    0.62
     arh
    0.62
     vair
    0.62
    POSITIVE LOGITS
     far
    1.74
     distance
    1.39
    far
    1.35
    way
    1.35
     way
    1.34
    distances
    1.33
    Distance
    1.31
    distance
    1.31
    远
    1.31
     farthest
    1.30
    Act Density 0.046%

    No Known Activations