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

    Neuronpedia

    INDEX
    Explanations

    moon and sun facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这里的
    0.45
     Parent
    0.40
     herein
    0.39
    的路
    0.39
     Configuration
    0.39
    ここ
    0.38
     Output
    0.38
    ভিল
    0.38
    ខាង
    0.37
     Configurations
    0.37
    POSITIVE LOGITS
     gimbal
    0.46
    нус
    0.45
    forder
    0.45
    massage
    0.42
     retaining
    0.39
    lesson
    0.39
    fortun
    0.39
     हमे
    0.39
    lysis
    0.38
     wielding
    0.38
    Act Density 0.000%

    No Known Activations