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

    Neuronpedia

    INDEX
    Explanations

    translating English text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    糖尿
    0.39
     होकर
    0.38
    ⃖
    0.37
     डायरेक्शन
    0.37
     hayan
    0.36
    दुर
    0.36
    とのこと
    0.36
    ným
    0.35
     하여
    0.35
    Rek
    0.35
    POSITIVE LOGITS
     feeds
    0.46
     cibo
    0.45
     foods
    0.44
    foods
    0.41
     limites
    0.40
     tı
    0.40
     improves
    0.39
     embedded
    0.38
     results
    0.38
     punishments
    0.37
    Act Density 0.001%

    No Known Activations