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

    Neuronpedia

    INDEX
    Explanations

    web page urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ihnachten
    -0.81
     كذلك
    -0.81
     Corning
    -0.78
    æng
    -0.77
    ឌ
    -0.77
    --}}
    -0.77
    ඬ
    -0.77
    baix
    -0.75
     jetta
    -0.75
    ophageal
    -0.75
    POSITIVE LOGITS
    Mnemonic
    0.94
    还是要
    0.86
     exact
    0.81
    ayaquil
    0.81
    Én
    0.79
    自体は
    0.79
     marca
    0.78
     porcentual
    0.78
    阳台
    0.77
     químico
    0.76
    Act Density 0.016%

    No Known Activations