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

    Neuronpedia

    INDEX
    Explanations

    programming library includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spiderX
    0.43
    пен
    0.41
    蹌
    0.39
     ഏറ്റവും
    0.39
    🈯
    0.38
    taobao
    0.38
     광고
    0.37
     fresher
    0.37
    sebastian
    0.37
    kyverno
    0.37
    POSITIVE LOGITS
     header
    0.53
     headers
    0.51
    /
    0.47
    Constants
    0.47
    unistd
    0.47
    defs
    0.46
     definitions
    0.46
    헤
    0.45
    header
    0.44
    Header
    0.44
    Act Density 0.008%

    No Known Activations