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

    Neuronpedia

    INDEX
    Explanations

    non-english text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /M
    -0.08
     Jacket
    -0.07
     Klo
    -0.07
    /K
    -0.07
     Natur
    -0.06
     vej
    -0.06
     apenas
    -0.06
     используется
    -0.06
    -entity
    -0.06
    (locale
    -0.06
    POSITIVE LOGITS
    독
    0.07
     FOLLOW
    0.07
    YEAR
    0.06
     marches
    0.06
    _RD
    0.06
    ्रदर
    0.06
    ありがとう
    0.06
    _sync
    0.06
    REM
    0.06
    -regexp
    0.06
    Act Density 0.055%

    No Known Activations