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

    Neuronpedia

    INDEX
    Explanations

    technical documentation snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Car
    0.69
    Car
    0.66
     LaTeX
    0.65
    hept
    0.64
     sy
    0.64
    руса
    0.61
    𝔬
    0.60
    валася
    0.60
     SIINFEKL
    0.60
     car
    0.60
    POSITIVE LOGITS
     اتمنى
    0.71
    atsiooni
    0.71
    များကို
    0.67
     المح
    0.66
    WHIT
    0.64
    ದು
    0.64
     επι
    0.64
    izaci
    0.64
    ަމ
    0.63
    टाइ
    0.63
    Act Density 0.077%

    No Known Activations