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

    Neuronpedia

    INDEX
    Explanations

    mean: hive: protection function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gifs
    0.87
     সমাধিতে
    0.82
    larla
    0.81
    Jill
    0.79
    聋
    0.78
    лями
    0.78
    Bec
    0.78
    તમ
    0.77
    ilesh
    0.77
    ÉRI
    0.76
    POSITIVE LOGITS
     (
    1.01
    ،
    0.90
     مذکور
    0.87
    ,
    0.87
     וא
    0.75
    వారం
    0.74
     +
    0.73
    ।
    0.72
     Lower
    0.72
    、
    0.72
    Act Density 0.381%

    No Known Activations