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

    Neuronpedia

    INDEX
    Explanations

    domain DNS resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鹿児
    0.43
     我的
    0.40
    ünüz
    0.38
     بعدها
    0.38
    শেখ
    0.37
    PROGRESS
    0.37
     требо
    0.36
     progressBar
    0.36
     سف
    0.36
    ikä
    0.36
    POSITIVE LOGITS
    #
    0.42
    Weil
    0.40
    可以看出
    0.40
     MFA
    0.39
     kial
    0.38
     dunkel
    0.38
     Jokes
    0.38
     hés
    0.38
     interrupts
    0.38
     Weil
    0.38
    Act Density 0.000%

    No Known Activations