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

    Neuronpedia

    INDEX
    Explanations

    special characters and arrows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ча
    0.85
     Cane
    0.80
    ⱪ
    0.72
     Charts
    0.71
     Castillo
    0.70
     Петра
    0.70
     Владимира
    0.70
    वर
    0.68
    פא
    0.68
    ха
    0.67
    POSITIVE LOGITS
    to
    0.86
    え
    0.85
     produkcji
    0.82
    ออนไลน์
    0.80
    しかし
    0.80
    き
    0.80
    AT
    0.79
    𝙄
    0.79
    クリスマス
    0.77
    micronaut
    0.77
    Act Density 0.003%

    No Known Activations