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

    Neuronpedia

    INDEX
    Explanations

    rarely, cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utama
    0.67
     건축
    0.64
    闡
    0.63
    歴
    0.63
     makers
    0.62
    ∵
    0.61
     Because
    0.60
     Building
    0.60
    機器
    0.59
     Manufacturer
    0.58
    POSITIVE LOGITS
    🤢
    0.81
     parfois
    0.79
     occasionally
    0.77
    🤮
    0.75
    😷
    0.73
    🙏🏻
    0.73
    🎟
    0.71
    ">⁡</
    0.70
     pedibusque
    0.70
     ascorbic
    0.69
    Act Density 0.002%

    No Known Activations