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

    Neuronpedia

    INDEX
    Explanations

    next, only, level, capt, ret, year, cloud, on, inside, lush

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חש
    0.34
     réfrig
    0.33
     बल
    0.33
    ⊰
    0.33
     кілько
    0.33
    櫻
    0.32
    сия
    0.31
    ˏ
    0.31
    ⦕
    0.31
     일으
    0.31
    POSITIVE LOGITS
     যাইত
    0.36
    मन
    0.35
    வான்
    0.34
     môn
    0.33
    ăn
    0.33
     மேற்கு
    0.31
     man
    0.31
     arc
    0.31
    ôn
    0.31
    φα
    0.31
    Act Density 0.002%

    No Known Activations