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

    Neuronpedia

    INDEX
    Explanations

    information about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    daq
    0.40
    dbc
    0.39
    yaf
    0.38
    앉
    0.38
    ရှ
    0.38
     संगठ
    0.37
    ნა
    0.37
     दृष्टिकोण
    0.36
     ။
    0.36
    ाइवेट
    0.36
    POSITIVE LOGITS
     будет
    0.44
     Bahkan
    0.43
     आणि
    0.42
    ຈາກ
    0.41
    ிகளும்
    0.41
    With
    0.41
     ameri
    0.40
     после
    0.40
    CON
    0.40
     ਅਤੇ
    0.40
    Act Density 0.004%

    No Known Activations