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

    Neuronpedia

    INDEX
    Explanations

    Traditionally, normally, what it means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kuwait
    0.40
    のための
    0.39
     महान
    0.39
    ղ
    0.38
    1
    0.38
    ਮ
    0.37
     Negro
    0.37
     أخ
    0.37
    мир
    0.36
    員の
    0.36
    POSITIVE LOGITS
     dampen
    0.56
    🌦
    0.47
    CHEMY
    0.46
    萂
    0.46
     увла
    0.46
     brisket
    0.46
    ColorEffects
    0.46
     nossos
    0.46
     stoichiometry
    0.45
    ၡ
    0.45
    Act Density 0.002%

    No Known Activations