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

    Neuronpedia

    INDEX
    Explanations

    existence outside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.75
    و
    0.71
    ו
    0.55
    か
    0.54
    Y
    0.54
    го
    0.50
    до
    0.50
    е
    0.50
    G
    0.50
    IN
    0.50
    POSITIVE LOGITS
    h
    0.68
     this
    0.64
    0
    0.60
     αυτή
    0.57
     you
    0.56
     actors
    0.56
     providers
    0.56
     yüksek
    0.56
     academics
    0.54
     is
    0.54
    Act Density 0.027%

    No Known Activations