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

    Neuronpedia

    INDEX
    Explanations

    comparing AI models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    榀
    0.40
    केट
    0.38
     serialized
    0.37
     viande
    0.36
     ভিন্ন
    0.36
    野球
    0.36
    周辺
    0.36
     гар
    0.35
     pname
    0.35
     verändert
    0.35
    POSITIVE LOGITS
     Fellow
    0.41
     আমিও
    0.40
     Astro
    0.40
    anni
    0.39
     Brew
    0.39
    âns
    0.39
    idina
    0.39
     лично
    0.39
     Astr
    0.38
     Cycl
    0.38
    Act Density 0.003%

    No Known Activations