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

    Neuronpedia

    INDEX
    Explanations

    requires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getDefaultSh
    0.73
     যেন
    0.71
    终于
    0.70
    的作用
    0.67
    इद
    0.66
    症
    0.63
    Throwable
    0.63
    こと
    0.60
     ች
    0.59
    終於
    0.59
    POSITIVE LOGITS
     requires
    5.26
     require
    5.04
     Requires
    4.75
     requiring
    4.75
    Requires
    4.64
    requires
    4.63
     Require
    4.59
    require
    4.57
     requiere
    4.29
    Require
    4.28
    Act Density 0.972%

    No Known Activations