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

    Neuronpedia

    INDEX
    Explanations

    abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Elect
    -0.07
     Gewer
    -0.07
     antibiotic
    -0.07
    δρο
    -0.07
    (?)
    -0.07
    सर
    -0.07
     suspension
    -0.07
     herb
    -0.07
    تی
    -0.07
    POSITIVE LOGITS
     เป็นต้น
    0.09
    Sometimes
    0.08
    (person
    0.08
     Sometimes
    0.08
     ঘোষ
    0.08
    ;)↵↵
    0.08
    (foo
    0.08
     гэсэн
    0.08
    entie
    0.08
    (expr
    0.08
    Act Density 0.018%

    No Known Activations