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

    Neuronpedia

    INDEX
    Explanations

    udp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Timestamp
    -0.08
     Troy
    -0.07
     turnout
    -0.07
     расход
    -0.07
     Graf
    -0.07
     Смотр
    -0.07
     Zionist
    -0.07
     patriot
    -0.07
     Prototype
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     oder
    0.07
    :self
    0.07
    Ubuntu
    0.07
    ekyll
    0.07
    adoop
    0.07
    Collider
    0.07
     אך
    0.06
    -leading
    0.06
     disparate
    0.06
    ellular
    0.06
    Act Density 0.002%

    No Known Activations