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

    Neuronpedia

    INDEX
    Explanations

    from other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    していきます
    1.32
    elabel
    1.19
    正在
    1.16
    𝕕
    1.15
    xido
    1.11
     kiểu
    1.11
    定
    1.11
    elom
    1.10
    hésitez
    1.10
    dater
    1.10
    POSITIVE LOGITS
    От
    1.19
    ்
    1.05
    𝖐
    0.94
    нской
    0.92
     сказать
    0.90
    াৎ
    0.90
    प्
    0.89
    KeyDown
    0.88
    ién
    0.88
     aid
    0.86
    Act Density 0.000%

    No Known Activations