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

    Neuronpedia

    INDEX
    Explanations

    who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    தேசம்
    0.38
     unqualified
    0.37
    டன்
    0.36
     விளக்கம்
    0.34
    준다
    0.33
    ForKey
    0.32
    ForRule
    0.32
    outez
    0.32
     શકાય
    0.32
    гатьох
    0.32
    POSITIVE LOGITS
     who
    0.74
     الذين
    0.74
    who
    0.63
     akik
    0.60
     kteří
    0.59
     whom
    0.59
     quienes
    0.58
     ktorí
    0.58
     whose
    0.57
     którzy
    0.57
    Act Density 0.021%

    No Known Activations