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

    Neuronpedia

    INDEX
    Explanations

    english or other language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beak
    0.38
    ÕES
    0.37
     NPA
    0.37
     impersonal
    0.36
     seben
    0.36
    pire
    0.36
    고자
    0.35
     selfless
    0.35
     predic
    0.34
     CPA
    0.34
    POSITIVE LOGITS
    ம
    0.46
    鞑
    0.43
     qualité
    0.42
     bình
    0.41
     पहाड़ी
    0.41
     adlı
    0.39
    ]//
    0.38
     সম
    0.38
    ровать
    0.38
     नंद
    0.37
    Act Density 0.000%

    No Known Activations