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

    Neuronpedia

    INDEX
    Explanations

    sequencing actions or components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਤ
    0.47
     չ
    0.45
     فر
    0.44
     عند
    0.44
     தான்
    0.44
    தான்
    0.43
     فن
    0.42
     خودرو
    0.42
     чи
    0.42
     دان
    0.42
    POSITIVE LOGITS
     coworkers
    0.46
     consumes
    0.46
     others
    0.46
    徉
    0.45
     reacts
    0.44
     iterator
    0.44
     playerCards
    0.44
    ():
    0.44
     ungroup
    0.43
     slows
    0.43
    Act Density 0.002%

    No Known Activations