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

    Neuronpedia

    INDEX
    Explanations

    explaining phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     избежать
    0.47
    RI
    0.47
     bylo
    0.45
    0.45
     trouver
    0.44
     corrente
    0.43
    E
    0.43
    EUI
    0.43
     Versuch
    0.42
     avait
    0.42
    POSITIVE LOGITS
     Brotherhood
    0.47
    𝐤
    0.41
    िकर
    0.40
    画像
    0.40
     emot
    0.39
    ‌هایی
    0.39
    嗳
    0.38
     hedon
    0.38
    𝐚
    0.38
    ів
    0.38
    Act Density 0.002%

    No Known Activations