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

    Neuronpedia

    INDEX
    Explanations

    ready physics input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल
    0.96
    ли
    0.81
    रु
    0.81
    ले
    0.77
    에
    0.75
     및
    0.74
    원
    0.71
     결
    0.71
     также
    0.71
     וי
    0.71
    POSITIVE LOGITS
    uses
    0.84
    ører
    0.82
    édrale
    0.82
    oled
    0.79
     policía
    0.78
    បញ្ចប់
    0.78
    spd
    0.78
     szabály
    0.77
    apé
    0.77
    ود
    0.77
    Act Density 0.001%

    No Known Activations