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

    Neuronpedia

    INDEX
    Explanations

    conversational AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arca
    0.40
     Aircraft
    0.39
     Complement
    0.39
     swag
    0.39
     dava
    0.39
     Có
    0.38
     documentación
    0.38
     partida
    0.38
    ड्डी
    0.38
     pack
    0.38
    POSITIVE LOGITS
    тали
    0.46
     الث
    0.44
     phrasing
    0.44
    Investing
    0.43
    كاته
    0.43
     doubtless
    0.41
    Investment
    0.41
    shopping
    0.40
    ショッピング
    0.40
    ファイ
    0.40
    Act Density 0.001%

    No Known Activations