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

    Neuronpedia

    INDEX
    Explanations

    Assign or convert units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    выше
    0.73
     boek
    0.71
     escrito
    0.68
    案例
    0.68
    आईटी
    0.68
    人民
    0.68
    ための
    0.67
    迷你
    0.66
     sever
    0.65
    Rp
    0.64
    POSITIVE LOGITS
     préalable
    0.81
     converts
    0.79
     তিনটি
    0.76
     ಈಗಾಗಲೇ
    0.74
    getahuan
    0.74
     convert
    0.73
     internalType
    0.73
    รู้จัก
    0.72
    ฏิ
    0.71
    ulous
    0.70
    Act Density 0.002%

    No Known Activations