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

    Neuronpedia

    INDEX
    Explanations

    is/has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @@@@
    -0.07
    Iron
    -0.07
     Iron
    -0.07
     Wag
    -0.07
     Campbell
    -0.07
     iron
    -0.07
     Michael
    -0.06
    家
    -0.06
    �
    -0.06
    خص
    -0.06
    POSITIVE LOGITS
     inters
    0.07
     Esto
    0.07
     elk
    0.06
     forgiven
    0.06
    集
    0.06
    фи
    0.06
     фунда
    0.06
    <Class
    0.06
     Manila
    0.06
     onChange
    0.06
    Act Density 0.030%

    No Known Activations