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

    Neuronpedia

    INDEX
    Explanations

    let X know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    -1.23
     amables
    -1.21
    бая
    -1.14
     Lê
    -1.12
     Фор
    -1.11
     requisitos
    -1.11
     onlyOwner
    -1.10
    ⸫
    -1.09
     that
    -1.09
    阂
    -1.08
    POSITIVE LOGITS
     say
    1.19
     話
    1.13
     know
    1.13
     詳細
    1.13
     définitivement
    1.09
     officiellement
    1.09
    正確
    1.06
     knows
    1.06
    gesterone
    1.05
    汌
    1.05
    Act Density 0.035%

    No Known Activations