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

    Neuronpedia

    INDEX
    Explanations

    loaded language and interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     electrician
    0.41
     tris
    0.40
     electricians
    0.40
     emble
    0.39
     penumpang
    0.39
     संतुलन
    0.39
     recapit
    0.39
    통산
    0.39
    หลัง
    0.39
     mantenimiento
    0.38
    POSITIVE LOGITS
     Content
    0.40
    コンテンツ
    0.40
     Annotated
    0.40
    Anagram
    0.39
     calculators
    0.39
     essays
    0.38
     বাংলা
    0.37
    Calculator
    0.37
    inker
    0.37
    Kan
    0.37
    Act Density 0.000%

    No Known Activations