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

    Neuronpedia

    INDEX
    Explanations

    URLs and website links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naïve
    0.26
     Quadrupèdes
    0.23
     callous
    0.22
    CTOGRAM
    0.22
     sadistic
    0.22
    出一
    0.22
     lógico
    0.22
     fecund
    0.21
     demás
    0.21
     Porém
    0.21
    POSITIVE LOGITS
    _
    0.44
    ↵
    0.42
    overview
    0.36
    /
    0.35
    /?
    0.35
    faq
    0.33
    -
    0.33
     and
    0.31
    \_
    0.31
     FAQs
    0.30
    Act Density 0.309%

    No Known Activations