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

    Neuronpedia

    INDEX
    Explanations

    JavaScript clear interval cleanup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কুট
    0.38
    вед
    0.38
     дея
    0.37
     नाइन
    0.36
    ोब
    0.36
     CORPOR
    0.36
    েলের
    0.35
     হিন
    0.35
    cav
    0.35
    頬
    0.35
    POSITIVE LOGITS
     require
    0.60
     requiring
    0.52
    require
    0.51
     requires
    0.47
     node
    0.44
     requirement
    0.43
     Inter
    0.42
     Require
    0.42
    Require
    0.41
     stylesheet
    0.41
    Act Density 0.000%

    No Known Activations