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

    Neuronpedia

    INDEX
    Explanations

    Importer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibile
    -0.07
    ucion
    -0.07
    支付宝
    -0.07
     greetings
    -0.07
    OK
    -0.07
    万博
    -0.07
    ￩
    -0.06
     futuro
    -0.06
    祖
    -0.06
     onViewCreated
    -0.06
    POSITIVE LOGITS
    (user
    0.08
    假日
    0.07
    Addr
    0.07
    -handler
    0.07
    .example
    0.07
     inconvenient
    0.07
     хотя
    0.07
     Complexity
    0.06
    -handle
    0.06
     Definition
    0.06
    Act Density 0.001%

    No Known Activations