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

    Neuronpedia

    INDEX
    Explanations

    expect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鸠
    -0.07
    ↵		
↵
    -0.07
    樗
    -0.07
    腒
    -0.07
    点缀
    -0.06
     Centre
    -0.06
     Sunder
    -0.06
     الشيخ
    -0.06
    être
    -0.06
     Cast
    -0.06
    POSITIVE LOGITS
     modification
    0.07
     اليمن
    0.07
    راج
    0.07
     jeopardy
    0.07
    략
    0.07
    (role
    0.06
    ram
    0.06
    랴
    0.06
    ㅚ
    0.06
    岩
    0.06
    Act Density 0.006%

    No Known Activations