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

    Neuronpedia

    INDEX
    Explanations

    fiction summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nedeniyle
    -0.07
    icode
    -0.06
    hin
    -0.06
    ляють
    -0.06
     非
    -0.06
    urar
    -0.06
    mdat
    -0.06
    ENCIL
    -0.06
    улю
    -0.06
    iks
    -0.06
    POSITIVE LOGITS
    лючается
    0.07
     COLLECTION
    0.06
    场
    0.06
    ::*;↵
    0.06
     крови
    0.06
     arom
    0.06
    site
    0.06
    _preferences
    0.06
     refriger
    0.06
    brain
    0.06
    Act Density 0.045%

    No Known Activations