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

    Neuronpedia

    INDEX
    Explanations

    dragon, oak, computer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    គឺ
    0.44
     अवे
    0.43
     Petit
    0.38
     સમયે
    0.38
     illustrations
    0.38
    时间的
    0.37
     ミニ
    0.36
     ها
    0.36
     सब्सक्राइब
    0.36
    ോടെ
    0.36
    POSITIVE LOGITS
    aldb
    0.44
    ochlor
    0.41
    炎
    0.39
    忧
    0.39
    प्याज
    0.38
    دو
    0.38
     warmup
    0.37
    ხმარ
    0.37
    ULAR
    0.37
    бору
    0.36
    Act Density 0.001%

    No Known Activations