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

    Neuronpedia

    INDEX
    Explanations

    cyber security

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অপর্ণ
    0.68
     ravel
    0.68
    ﺲ
    0.67
     DataTypes
    0.64
     অবি
    0.64
     unifying
    0.63
     Eurostile
    0.63
    ковое
    0.63
    зё
    0.62
    জিওথের
    0.61
    POSITIVE LOGITS
     loos
    0.65
    얀
    0.59
     occurred
    0.55
    앞
    0.54
    ály
    0.54
    อื่น
    0.52
    agan
    0.52
    _;
    0.52
    白い
    0.52
    早
    0.52
    Act Density 0.000%

    No Known Activations