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

    Neuronpedia

    INDEX
    Explanations

    training and education

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    government
    -0.08
    جاب
    -0.07
     autoimmune
    -0.07
    疟
    -0.07
    -rate
    -0.07
    ropping
    -0.07
    iode
    -0.07
    ten
    -0.07
    topic
    -0.07
    中国的
    -0.07
    POSITIVE LOGITS
    啦
    0.07
    おすす
    0.07
     และ
    0.07
     któ
    0.07
    (Calendar
    0.07
    .coeff
    0.06
    -delay
    0.06
     refactor
    0.06
    WithData
    0.06
    执导
    0.06
    Act Density 0.046%

    No Known Activations