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

    Neuronpedia

    INDEX
    Explanations

    factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Scenes
    0.42
     Scenes
    0.40
    linejoin
    0.40
    颌
    0.39
     शौक
    0.39
    owaniem
    0.38
     escenas
    0.38
     पीड़ितों
    0.38
     الهدف
    0.38
     روحانی
    0.38
    POSITIVE LOGITS
     factors
    2.70
    Factors
    2.33
     Factors
    2.31
    factors
    2.31
     factores
    2.30
     facteurs
    2.25
    因素
    2.20
     fatores
    2.20
     факторы
    2.16
     fattori
    2.13
    Act Density 0.038%

    No Known Activations