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

    Neuronpedia

    INDEX
    Explanations

    other, different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contemplation
    0.83
    BibitemOpen
    0.80
    жение
    0.75
    ″
    0.74
     lượng
    0.74
    çük
    0.73
     leptonic
    0.73
     leggere
    0.72
     korišten
    0.72
    0.72
    POSITIVE LOGITS
    worldly
    0.78
    t
    0.78
    ar
    0.76
    te
    0.75
    те
    0.75
    teste
    0.75
    en
    0.68
    differ
    0.68
    ric
    0.68
    ство
    0.67
    Act Density 0.285%

    No Known Activations