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

    Neuronpedia

    INDEX
    Explanations

    Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tactic
    -0.08
    ổng
    -0.07
     sour
    -0.07
     POLITICO
    -0.07
    defer
    -0.06
    quential
    -0.06
    ān
    -0.06
    角色
    -0.06
    卡
    -0.06
     Behaviour
    -0.06
    POSITIVE LOGITS
     승
    0.07
     sealed
    0.07
     등을
    0.07
    اکی
    0.07
     区
    0.07
     важно
    0.06
    ा↵↵
    0.06
    -нибудь
    0.06
     unnecessarily
    0.06
    faculty
    0.06
    Act Density 0.000%

    No Known Activations