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

    Neuronpedia

    INDEX
    Explanations

    code, foreign words, names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SqlParameter
    -0.62
    IMENTO
    -0.57
     متعلقه
    -0.54
    WireFormatLite
    -0.52
     MAV
    -0.48
    CompilerServices
    -0.47
    LEGGI
    -0.46
    gwt
    -0.46
    Filmographie
    -0.44
     sqlSession
    -0.44
    POSITIVE LOGITS
    legi
    0.59
    Становништво
    0.58
    انتهای
    0.58
    Portail
    0.54
     Reli
    0.53
     MainAxisSize
    0.53
     Noel
    0.52
    aderas
    0.52
    ://$
    0.52
     refor
    0.52
    Act Density 0.000%

    No Known Activations