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

    Neuronpedia

    INDEX
    Explanations

    code explanations and snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಧಿ
    0.79
     अर्थात्
    0.76
     ίδ
    0.75
    ರಿಸ
    0.74
    ပြီ
    0.74
    に出
    0.74
     உ
    0.74
     Nhi
    0.73
     установлен
    0.72
     установи
    0.72
    POSITIVE LOGITS
     bridge
    0.69
    Thats
    0.69
    olding
    0.67
    ﺋ
    0.66
    そういう
    0.65
    
    0.65
    ,$$
    0.64
     ander
    0.63
    
    0.63
    According
    0.63
    Act Density 0.042%

    No Known Activations