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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prevención
    0.43
     ово
    0.42
     முயற்
    0.41
     аспек
    0.41
     futur
    0.39
     चेंजेस
    0.39
     vacanam
    0.39
    IFT
    0.39
     څرنګ
    0.39
     конвер
    0.39
    POSITIVE LOGITS
    сті
    0.43
     overheating
    0.41
    同时
    0.41
    “
    0.40
    right
    0.40
    yphenyl
    0.40
    sembly
    0.39
    nti
    0.39
    nail
    0.39
    zant
    0.38
    Act Density 10.968%

    No Known Activations