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

    Neuronpedia

    INDEX
    Explanations

    escalation, vulnerable, oxygen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ≺
    0.44
     määr
    0.41
     sabía
    0.39
    ުރ
    0.39
     disordered
    0.39
     melee
    0.39
    CTAssert
    0.38
     Euclidean
    0.38
     للصف
    0.38
     контроли
    0.38
    POSITIVE LOGITS
    gy
    0.43
    gina
    0.41
     dav
    0.40
    amish
    0.39
    findOneAndUpdate
    0.39
    DAV
    0.39
    되었습니다
    0.38
     '!
    0.38
     fut
    0.37
    ding
    0.36
    Act Density 0.000%

    No Known Activations