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

    Neuronpedia

    INDEX
    Explanations

    classical literature or programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     желе
    0.57
     Вене
    0.49
     retinol
    0.47
     атом
    0.46
     инфра
    0.45
    }$.
    0.45
    фра
    0.44
     аппарат
    0.44
    ilion
    0.44
     радиа
    0.44
    POSITIVE LOGITS
     outputPath
    0.42
     declared
    0.42
     declaratory
    0.40
     Secretariat
    0.40
     Salaam
    0.39
    セックス
    0.39
     Declar
    0.39
     Password
    0.38
     decisive
    0.38
     onus
    0.38
    Act Density 0.003%

    No Known Activations