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

    Neuronpedia

    INDEX
    Explanations

    placeholder identifier "AA"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    羢
    0.37
    :‏
    0.36
    ിലൂടെ
    0.35
    нология
    0.35
    Watercolor
    0.34
    ၻ
    0.33
     ограничения
    0.33
    CubeSize
    0.33
    綢
    0.33
    耔
    0.33
    POSITIVE LOGITS
    g
    0.44
     made
    0.39
     j
    0.37
     me
    0.37
     AA
    0.37
     K
    0.37
    w
    0.36
    ip
    0.36
     sa
    0.36
    AA
    0.36
    Act Density 0.000%

    No Known Activations