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

    Neuronpedia

    INDEX
    Explanations

    (s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detail
    -0.07
     hott
    -0.06
     fame
    -0.06
    semester
    -0.06
     gathered
    -0.06
     Gesch
    -0.06
    خرج
    -0.06
     node
    -0.06
     scanf
    -0.06
    ucceed
    -0.06
    POSITIVE LOGITS
    不得
    0.07
    ें।
    0.07
     ทอง
    0.07
    arian
    0.07
    vements
    0.07
     iam
    0.06
     Argentine
    0.06
     comprar
    0.06
    �
    0.06
    *'
    0.06
    Act Density 0.001%

    No Known Activations