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

    Neuronpedia

    INDEX
    Explanations

    wikipedia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    初期
    0.77
     初期
    0.69
    antara
    0.67
     초기
    0.63
    initial
    0.63
    蹿
    0.62
    sema
    0.62
    Initial
    0.61
    솔
    0.61
    innamon
    0.60
    POSITIVE LOGITS
     আওয়
    0.61
    etière
    0.60
     Ambient
    0.59
    TDto
    0.58
     தாண்ட
    0.58
    パナソニック
    0.57
    ApiClient
    0.57
     misión
    0.57
     Trench
    0.56
     Vitt
    0.56
    Act Density 0.137%

    No Known Activations