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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Loco
    0.43
    ⠄
    0.41
     водо
    0.39
     tố
    0.39
    颶
    0.39
     Tribes
    0.38
    ၉
    0.38
    動力
    0.37
     Trek
    0.36
    ច្រ
    0.36
    POSITIVE LOGITS
     stalls
    0.44
     (*)
    0.38
     "*****
    0.38
     stall
    0.38
     lain
    0.37
     editor
    0.37
     descanso
    0.37
    shaw
    0.35
     sem
    0.35
     व्य
    0.35
    Act Density 0.000%

    No Known Activations