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

    Neuronpedia

    INDEX
    Explanations

    speak or ask you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.75
     crucial
    0.67
     huge
    0.58
    /
    0.57
     or
    0.55
     data
    0.54
     incredible
    0.53
     emerging
    0.53
     emerg
    0.53
    0.52
    POSITIVE LOGITS
     あなた
    0.92
    あなたが
    0.88
    あなたの
    0.86
    你的
    0.80
    YOU
    0.79
    あなた
    0.78
     당신
    0.78
    你有
    0.75
     вас
    0.74
    Your
    0.73
    Act Density 0.022%

    No Known Activations