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

    Neuronpedia

    INDEX
    Explanations

    sword drawbacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jahter
    0.41
    εν
    0.41
    지를
    0.39
    ﻨ
    0.39
    েব
    0.38
    多元
    0.37
    effectuer
    0.37
    제를
    0.37
    ौरा
    0.36
     "/",
    0.36
    POSITIVE LOGITS
     drawback
    0.73
     downsides
    0.72
     drawbacks
    0.71
     requires
    0.71
     downside
    0.70
     Requires
    0.67
     inconvén
    0.61
     require
    0.61
     requiere
    0.60
     risks
    0.59
    Act Density 0.219%

    No Known Activations