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

    Neuronpedia

    INDEX
    Explanations

    nameservers, domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bark
    0.39
     INT
    0.37
     Mos
    0.36
     Ib
    0.36
     Har
    0.35
     Trio
    0.35
     commence
    0.35
     Anders
    0.35
    MOS
    0.35
    \-
    0.35
    POSITIVE LOGITS
    öffentlichung
    0.44
    📛
    0.42
     قسمت
    0.40
    znego
    0.40
    Парт
    0.40
     FormGroup
    0.39
    원본파일명
    0.39
     legitim
    0.39
    товый
    0.39
     Parfum
    0.39
    Act Density 0.003%

    No Known Activations