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

    Neuronpedia

    INDEX
    Explanations

    common causes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    если
    0.48
     якщо
    0.48
     případě
    0.46
    अगर
    0.46
    utenção
    0.45
    itabbo
    0.45
    inguém
    0.45
     Якщо
    0.44
    ují
    0.44
     поддержку
    0.43
    POSITIVE LOGITS
     the
    0.53
     computer
    0.51
     electronic
    0.48
     planar
    0.47
     grap
    0.47
    ,
    0.47
     several
    0.46
     object
    0.46
    :
    0.46
     Euclidean
    0.46
    Act Density 0.001%

    No Known Activations