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

    Neuronpedia

    INDEX
    Explanations

    php code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTS
    0.47
    钿
    0.44
     வான
    0.42
    spiderX
    0.41
     يد
    0.40
    ادرة
    0.40
    ]【
    0.40
    ᓐ
    0.40
    ܂
    0.39
    ത്തുന്ന
    0.38
    POSITIVE LOGITS
    s
    0.48
    if
    0.46
     that
    0.45
    ise
    0.44
     tell
    0.43
    run
    0.42
    len
    0.41
    r
    0.40
    sz
    0.40
    ert
    0.40
    Act Density 0.001%

    No Known Activations