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

    Neuronpedia

    INDEX
    Explanations

    compliance and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𐰇
    0.47
     snapshots
    0.46
    룔
    0.41
     arithmetic
    0.41
    }}=
    0.40
    unless
    0.40
    지의
    0.40
    ****/
    0.39
    byteArray
    0.39
     startGame
    0.38
    POSITIVE LOGITS
     Now
    0.80
     now
    0.72
    Now
    0.69
     same
    0.64
    now
    0.64
     Same
    0.64
    same
    0.63
     Thank
    0.61
     Another
    0.61
    Same
    0.56
    Act Density 0.000%

    No Known Activations