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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Usu
    0.44
    дың
    0.43
    ിക
    0.42
    els
    0.41
    isor
    0.40
    えられる
    0.40
    onics
    0.39
    бота
    0.39
    brevi
    0.39
    ूस
    0.39
    POSITIVE LOGITS
     ","
    0.45
     Rheumat
    0.43
     couches
    0.42
     Jacques
    0.41
     Cyprus
    0.41
     tout
    0.40
     чемпионаты
    0.40
     cowboy
    0.39
     paraly
    0.39
     ™
    0.39
    Act Density 0.008%

    No Known Activations