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

    Neuronpedia

    INDEX
    Explanations

    configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     לבחור
    -0.07
    هو
    -0.07
    	RETURN
    -0.07
    dro
    -0.07
    澳大利亚
    -0.07
     ).↵↵
    -0.07
    ชนะ
    -0.07
     Comparable
    -0.07
    centration
    -0.06
    Implement
    -0.06
    POSITIVE LOGITS
     flawless
    0.08
    conto
    0.07
     newIndex
    0.07
    ሉ
    0.07
    퀵
    0.06
    _cg
    0.06
    ах
    0.06
    学习成绩
    0.06
    charted
    0.06
     adulti
    0.06
    Act Density 0.002%

    No Known Activations