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

    Neuronpedia

    INDEX
    Explanations

    compute **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.39
    ts
    0.33
    treas
    0.32
    hor
    0.31
    tm
    0.31
    著
    0.31
    trends
    0.31
    t
    0.31
    cultures
    0.30
    drift
    0.30
    POSITIVE LOGITS
     storage
    0.42
     ノ
    0.40
     Storage
    0.38
     *}\
    0.38
     Debye
    0.37
     arched
    0.37
     بخ
    0.36
     自
    0.36
     チ
    0.36
     jaundice
    0.36
    Act Density 0.000%

    No Known Activations