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

    Neuronpedia

    INDEX
    Explanations

    conditioned upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ថ្
    0.27
     mathemat
    0.24
     konfigur
    0.23
    睿
    0.23
     estrat
    0.23
     düşün
    0.22
     bilan
    0.22
     giz
    0.22
    リック
    0.22
     estet
    0.22
    POSITIVE LOGITS
     wenn
    0.38
     когда
    0.38
     when
    0.36
     якщо
    0.35
     cuando
    0.34
     khi
    0.34
     если
    0.34
    wenn
    0.33
    cuando
    0.33
    หาก
    0.32
    Act Density 0.000%

    No Known Activations