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

    Neuronpedia

    INDEX
    Explanations

    SQL variable declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FUNCTIONS
    0.44
    Function
    0.39
     Functions
    0.39
     функций
    0.39
    функ
    0.38
     Gilman
    0.38
    ನ್‌
    0.37
    Functions
    0.36
    Convert
    0.36
    നിൽ
    0.36
    POSITIVE LOGITS
     fridge
    0.43
     tertiary
    0.40
     Rother
    0.39
     alleging
    0.39
     MLS
    0.39
     Ott
    0.39
     quartier
    0.39
     Turqu
    0.38
    stra
    0.38
     explaining
    0.38
    Act Density 0.002%

    No Known Activations