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

    Neuronpedia

    INDEX
    Explanations

    code/database output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -machine
    -0.09
    瓘
    -0.07
    писыва
    -0.07
    dataType
    -0.07
    -provider
    -0.07
    一年级
    -0.06
    医用
    -0.06
     Zambia
    -0.06
    -dis
    -0.06
    cluir
    -0.06
    POSITIVE LOGITS
    Coordinates
    0.07
    ação
    0.07
     gồm
    0.07
    岛上
    0.06
    Eat
    0.06
    Agent
    0.06
    AL
    0.06
    ATIONS
    0.06
    ===
    0.06
    #↵
    0.06
    Act Density 0.022%

    No Known Activations