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

    Neuronpedia

    INDEX
    Explanations

    logging configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ქ
    1.75
    ר
    1.72
    cake
    1.64
    Sincerely
    1.63
    ᴄ
    1.59
    /−
    1.59
    स्पति
    1.58
    า
    1.56
    ători
    1.55
    кої
    1.54
    POSITIVE LOGITS
    psz
    1.75
    den
    1.75
    mente
    1.71
     bä
    1.69
     acredit
    1.69
     kurz
    1.69
    ंगिक
    1.66
     zalo
    1.63
     focal
    1.63
    dana
    1.62
    Act Density 0.001%

    No Known Activations