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

    Neuronpedia

    INDEX
    Explanations

    specific concepts or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟋
    0.48
    yiz
    0.44
     يح
    0.43
    鑼
    0.43
     heavyweight
    0.43
     harap
    0.43
     Heart
    0.43
     promet
    0.42
     серде
    0.42
    NN
    0.42
    POSITIVE LOGITS
    ября
    0.46
     lay
    0.43
     binders
    0.43
     Statutes
    0.42
    志愿
    0.42
     Magazines
    0.42
    тся
    0.41
    cnpj
    0.40
    ட்
    0.40
     rehears
    0.39
    Act Density 0.001%

    No Known Activations