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

    Neuronpedia

    INDEX
    Explanations

    here's how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.77
    ل
    0.74
     untersucht
    0.69
    ደር
    0.63
    ا
    0.62
    ত
    0.62
     clor
    0.62
     außerhalb
    0.60
    و
    0.59
     embarrassed
    0.58
    POSITIVE LOGITS
    bodyParser
    0.72
    OHAMA
    0.72
    ness
    0.71
    date
    0.70
    news
    0.69
    ues
    0.68
    답니다
    0.68
    garh
    0.68
    nya
    0.67
     Panorama
    0.66
    Act Density 0.001%

    No Known Activations