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

    Neuronpedia

    INDEX
    Explanations

    Statistical comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARATION
    -0.07
    _equiv
    -0.06
    Handle
    -0.06
    elier
    -0.06
    judge
    -0.06
     imz
    -0.06
    ільки
    -0.06
    _program
    -0.06
    (inner
    -0.06
     одного
    -0.06
    POSITIVE LOGITS
    StateManager
    0.06
     mistakenly
    0.06
    !'↵
    0.06
    (array
    0.06
    �
    0.06
    责任
    0.06
    [^
    0.06
     glGen
    0.06
    /'↵
    0.06
    %^
    0.06
    Act Density 0.015%

    No Known Activations