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

    Neuronpedia

    INDEX
    Explanations

    news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ීම්
    0.40
     spa
    0.39
    seit
    0.39
    guas
    0.38
    emos
    0.38
     fern
    0.38
    сур
    0.38
    缝
    0.38
     spikes
    0.38
    :‏
    0.38
    POSITIVE LOGITS
     hang
    0.46
     Half
    0.42
    祐
    0.39
    aint
    0.39
     ጥላ
    0.38
    Half
    0.38
    東海
    0.38
     More
    0.37
     Royal
    0.37
     disastrous
    0.36
    Act Density 0.001%

    No Known Activations