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

    Neuronpedia

    INDEX
    Explanations

    HPC: or ADSs:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     externas
    0.60
    鲟
    0.55
    哳
    0.54
    ों
    0.52
    ▟
    0.52
    蒎
    0.52
     stadiums
    0.50
     preparar
    0.50
     académ
    0.49
     wetensch
    0.49
    POSITIVE LOGITS
    。
    0.61
    :
    0.55
    ing
    0.49
     and
    0.47
    1
    0.47
    ↵↵
    0.47
    and
    0.47
     وليس
    0.46
    ↵↵↵
    0.46
    ut
    0.45
    Act Density 0.000%

    No Known Activations