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

    Neuronpedia

    INDEX
    Explanations

    sneak peek

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dele
    0.46
     let
    0.42
     flaw
    0.41
     Leafs
    0.39
     Berm
    0.38
    brough
    0.38
     Leaves
    0.38
    戞
    0.37
    닉
    0.37
    BRAS
    0.37
    POSITIVE LOGITS
    दमी
    0.44
    Statistical
    0.44
    Scul
    0.42
     Scul
    0.40
     Statistical
    0.39
    齙
    0.39
     Inorganic
    0.39
    вати
    0.39
    ی
    0.39
    ുന്നത്
    0.39
    Act Density 0.001%

    No Known Activations