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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     первого
    -0.08
    |}↵
    -0.07
     diferencia
    -0.07
     ());↵
    -0.07
    licensed
    -0.07
     hö
    -0.07
     foo
    -0.07
    _Equals
    -0.06
    放大
    -0.06
     systematic
    -0.06
    POSITIVE LOGITS
    BSITE
    0.07
    Holiday
    0.07
    致力于
    0.07
     birthday
    0.07
     Basement
    0.06
    盛典
    0.06
    ir
    0.06
    /story
    0.06
    泖
    0.06
    erties
    0.06
    Act Density 0.001%

    No Known Activations