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

    Neuronpedia

    INDEX
    Explanations

    difficulty or intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    semibold
    1.01
    ᅱ
    0.98
    confusion
    0.94
     ondas
    0.93
     Ответ
    0.91
     डिजा
    0.91
    cosmos
    0.90
     сме
    0.89
    ยาว
    0.89
    Daisy
    0.87
    POSITIVE LOGITS
    wired
    1.34
     পরিশ্রম
    1.22
    Hard
    1.14
     pressed
    1.13
    nosed
    1.11
    pressed
    1.08
     khăn
    1.05
     Hard
    1.03
    coded
    1.03
    hitting
    1.02
    Act Density 0.122%

    No Known Activations