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

    Neuronpedia

    INDEX
    Explanations

    something else; something faintly; something you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ir
    2.73
    op
    2.69
    ão
    2.66
    od
    2.53
    ad
    2.42
    r
    2.36
    il
    2.31
    anh
    2.25
    c
    2.23
    ra
    2.22
    POSITIVE LOGITS
    ки
    3.72
    り
    3.00
    вання
    2.22
    いた
    2.17
    ารย์
    1.99
     else
    1.88
    ⺝
    1.88
    ня
    1.88
    daki
    1.87
    garten
    1.87
    Act Density 0.185%

    No Known Activations