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

    Neuronpedia

    INDEX
    Explanations

    docstrings with arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    darkMode
    0.42
    en
    0.42
    ನೇ
    0.41
    endo
    0.40
    atures
    0.39
     bowels
    0.38
     heather
    0.38
    ნიშვნ
    0.38
     bothering
    0.38
    slee
    0.38
    POSITIVE LOGITS
     roku
    0.43
    此之外
    0.41
     направ
    0.39
     ActionListener
    0.39
     cnt
    0.38
     verificación
    0.38
     заря
    0.38
    人材
    0.37
     включает
    0.36
    お金
    0.36
    Act Density 0.043%

    No Known Activations