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

    Neuronpedia

    INDEX
    Explanations

    AnyDesk, Anytown, AnyLogic, AnyConnect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     básico
    0.46
     básicos
    0.45
    यों
    0.40
    ាតុ
    0.39
    基本
    0.39
     cuadrados
    0.39
     קר
    0.38
    鳎
    0.38
    慨
    0.38
    لق
    0.38
    POSITIVE LOGITS
    lysis
    0.46
    where
    0.46
    time
    0.45
    ACE
    0.44
    place
    0.43
     arbitrary
    0.43
    ösung
    0.43
    Story
    0.42
    how
    0.41
    haust
    0.41
    Act Density 0.001%

    No Known Activations