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

    Neuronpedia

    INDEX
    Explanations

    my followed by a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    2.15
    ul
    1.84
     곳
    1.72
    <0xBB>
    1.66
    راء
    1.65
    yen
    1.57
    𝑖
    1.55
    it
    1.51
    記事
    1.48
     besteht
    1.47
    POSITIVE LOGITS
     own
    2.73
    rtle
    2.04
     Own
    1.97
    opically
    1.94
    ocardial
    1.89
    riad
    1.85
    SELF
    1.80
     onPressed
    1.75
    asthenia
    1.72
    ਲੇ
    1.72
    Act Density 0.496%

    No Known Activations