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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queim
    0.26
     Devlet
    0.26
     Veamos
    0.26
     Lembrando
    0.25
    澼
    0.24
     Zeich
    0.24
     الجه
    0.24
    तरीय
    0.24
     Estudios
    0.24
     Até
    0.24
    POSITIVE LOGITS
     или
    0.39
     或
    0.39
    或
    0.39
     หรือ
    0.36
     hoặc
    0.35
     ಅಥವಾ
    0.35
     ឬ
    0.35
     বা
    0.34
     లేదా
    0.33
    或者
    0.33
    Act Density 0.111%

    No Known Activations