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

    Neuronpedia

    INDEX
    Explanations

    address information

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    败
    0.67
    敗
    0.64
    段階
    0.63
    ChooseCharacter
    0.63
     prequel
    0.61
     объяви
    0.59
    付费
    0.58
     blame
    0.57
     製
    0.57
    責任
    0.56
    POSITIVE LOGITS
    ضي
    0.70
    elni
    0.63
     поддержки
    0.60
    ;++
    0.60
     retrieves
    0.59
    minas
    0.58
     wen
    0.57
     সমর্থনে
    0.57
    entious
    0.57
    梩
    0.55
    Act Density 0.000%

    No Known Activations