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

    Neuronpedia

    INDEX
    Explanations

    column structure and content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    邦
    -0.82
    FINAL
    -0.78
     السعود
    -0.78
    禺
    -0.76
    reszcie
    -0.76
     Consolidation
    -0.75
    íně
    -0.75
    又
    -0.74
    兵
    -0.74
    血
    -0.73
    POSITIVE LOGITS
    CardView
    0.96
    队友
    0.90
    kete
    0.84
     ~=
    0.80
    hover
    0.79
     col
    0.77
     Trotz
    0.77
    的服务
    0.76
     remarqu
    0.74
    してほしい
    0.73
    Act Density 0.008%

    No Known Activations