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

    Neuronpedia

    INDEX
    Explanations

    goals and achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     executed
    0.64
     milit
    0.57
     businesses
    0.57
     murdered
    0.57
    AndUpdate
    0.56
     ausgeführt
    0.55
     completed
    0.55
     purported
    0.55
    DropDownItems
    0.54
     Tours
    0.54
    POSITIVE LOGITS
     شدن
    0.64
    uffin
    0.58
    を目指
    0.58
    !
    0.58
    目標
    0.57
    ំប
    0.57
    łej
    0.57
    へと
    0.56
    avier
    0.55
     vorbere
    0.55
    Act Density 0.084%

    No Known Activations