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

    Neuronpedia

    INDEX
    Explanations

    thanks for or thanks to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.95
    on
    0.95
    b
    0.82
    ्त
    0.76
    iat
    0.73
    t
    0.73
     linebacker
    0.70
     collider
    0.69
    ле
    0.68
    анд
    0.68
    POSITIVE LOGITS
    ль
    0.90
    し
    0.89
     I
    0.86
    在
    0.70
    с
    0.68
    ઈ
    0.68
    رف
    0.67
    ます
    0.67
    จะ
    0.66
    通过
    0.65
    Act Density 0.007%

    No Known Activations