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

    Neuronpedia

    INDEX
    Explanations

    Coding/programming context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    沉浸
    -0.07
    ología
    -0.07
    exercise
    -0.07
    明年
    -0.07
    的地位
    -0.07
     business
    -0.06
    売り
    -0.06
     educação
    -0.06
     ecology
    -0.06
     safety
    -0.06
    POSITIVE LOGITS
     delegate
    0.06
    (enable
    0.06
     Som
    0.06
     PO
    0.06
     requ
    0.06
    յ
    0.06
     SUCH
    0.06
     Including
    0.06
     Include
    0.06
    שוט
    0.06
    Act Density 0.033%

    No Known Activations