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

    Neuronpedia

    INDEX
    Explanations

    Reusing and repetition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Boolean
    -0.08
     seating
    -0.07
     veto
    -0.06
    _BRANCH
    -0.06
    柄
    -0.06
    iseconds
    -0.06
     verte
    -0.06
     труд
    -0.06
    8
    -0.06
    ولی
    -0.06
    POSITIVE LOGITS
    ationally
    0.07
    :numel
    0.07
     thẻ
    0.06
     här
    0.06
     numbered
    0.06
    /questions
    0.06
    �
    0.06
     декоратив
    0.06
    ”。↵↵
    0.06
    	pos
    0.06
    Act Density 0.236%

    No Known Activations