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

    Neuronpedia

    INDEX
    Explanations

    why

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .RequestMethod
    -0.07
    olu
    -0.06
     Lig
    -0.06
    hin
    -0.06
     маг
    -0.06
     Resident
    -0.06
     sicher
    -0.06
     Metropolitan
    -0.06
    Padding
    -0.06
     shade
    -0.06
    POSITIVE LOGITS
     maxSize
    0.07
     infinity
    0.07
     الاتحاد
    0.07
     �
    0.07
    童
    0.07
    ><!--
    0.06
    命令
    0.06
                ↵↵
    0.06
    ↵    ↵↵
    0.06
     squadron
    0.06
    Act Density 0.003%

    No Known Activations