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

    Neuronpedia

    INDEX
    Explanations

    absence of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᴘ
    0.75
    ات
    0.69
    ز
    0.69
    ☑
    0.63
     wisata
    0.61
    ᴍ
    0.61
    <0x9C>
    0.61
    ्य
    0.60
    С
    0.59
     silam
    0.59
    POSITIVE LOGITS
    nobyl
    0.73
    कोई
    0.63
    aurants
    0.62
    '"
    0.61
    nancy
    0.58
    0.58
    Aa
    0.57
    та
    0.57
     ничего
    0.56
    ilab
    0.56
    Act Density 0.016%

    No Known Activations