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

    Neuronpedia

    INDEX
    Explanations

    comma followed by and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,//
    0.83
    」、「
    0.80
    /
    0.78
    ,
    0.78
    ,/
    0.77
    ”、“
    0.76
    ፣
    0.68
    )、
    0.66
    ,|\
    0.66
    ierte
    0.66
    POSITIVE LOGITS
     and
    2.18
     आणि
    1.96
     और
    1.93
     અને
    1.89
     এবং
    1.86
     и
    1.85
     ಮತ್ತು
    1.82
    และ
    1.82
     ਅਤੇ
    1.81
     và
    1.75
    Act Density 0.685%

    No Known Activations