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

    Neuronpedia

    INDEX
    Explanations

    fantasy/adventure plot descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mm
    -0.07
     besser
    -0.06
     �
    -0.06
     meg
    -0.06
    )");↵↵
    -0.06
    نتاج
    -0.06
     tutto
    -0.06
     Serie
    -0.06
     однов
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .proc
    0.07
     referencing
    0.06
    Caps
    0.06
    crew
    0.06
     scape
    0.06
    Event
    0.06
    unlock
    0.06
     Font
    0.06
     spoof
    0.06
     Kentucky
    0.06
    Act Density 0.073%

    No Known Activations