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

    Neuronpedia

    INDEX
    Explanations

    html doctype declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ><
    0.41
    Ћ
    0.40
    bibli
    0.39
    லிய
    0.39
     modernize
    0.39
    umd
    0.39
    omegal
    0.38
     Thurs
    0.38
     >=
    0.37
    ții
    0.37
    POSITIVE LOGITS
     효
    0.41
     ذخ
    0.39
     خصوصی
    0.38
     ಸ್ಥಾನ
    0.38
     esters
    0.38
    धित
    0.38
     স্থ
    0.37
     body
    0.37
     adherence
    0.36
    Weight
    0.36
    Act Density 0.001%

    No Known Activations