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

    Neuronpedia

    INDEX
    Explanations

    instructions or prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sh
    0.74
     fhe
    0.67
    </tbody>
    0.65
    фер
    0.64
    HER
    0.64
    蚪
    0.64
    itution
    0.63
    SCH
    0.62
    ൃശ
    0.62
    φη
    0.62
    POSITIVE LOGITS
    τί
    0.72
    ας
    0.70
    uosa
    0.70
    एनएल
    0.68
     colocando
    0.68
     ƒ
    0.68
     yanı
    0.67
    痩
    0.67
    ாடு
    0.67
    λογία
    0.66
    Act Density 0.033%

    No Known Activations