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

    Neuronpedia

    INDEX
    Explanations

    Half-Life, Half-Elf

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     словарь
    0.79
     irrevocable
    0.78
    風格
    0.74
    तह
    0.73
    ITwitter
    0.73
     Syllabus
    0.72
    اے
    0.72
     televisión
    0.72
     anxiety
    0.71
     Sprache
    0.71
    POSITIVE LOGITS
    pipe
    0.78
    Sum
    0.74
    phenoxy
    0.74
    breed
    0.71
     হানি
    0.71
    ضاع
    0.71
    ords
    0.69
     sums
    0.69
    Height
    0.69
    delen
    0.69
    Act Density 0.006%

    No Known Activations