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

    Neuronpedia

    INDEX
    Explanations

    Ending FT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onto
    0.42
     Vou
    0.39
     decomp
    0.39
    decomp
    0.38
     दरों
    0.38
     ravel
    0.38
    كال
    0.38
    idious
    0.37
    amaan
    0.37
     Idris
    0.36
    POSITIVE LOGITS
     〔
    0.42
     trending
    0.38
    ابس
    0.38
    లి
    0.38
     Trending
    0.38
     greenish
    0.37
    тре
    0.37
    传媒
    0.37
     reactive
    0.37
     tone
    0.36
    Act Density 0.000%

    No Known Activations