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

    Neuronpedia

    INDEX
    Explanations

    512

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     garnish
    -0.07
     nationalism
    -0.07
    PAS
    -0.07
    Mor
    -0.07
    ตั้ง
    -0.07
     बो
    -0.07
    utation
    -0.07
    ्रिय
    -0.07
     bloqueo
    -0.07
     ठीक
    -0.07
    POSITIVE LOGITS
     cubes
    0.08
     cube
    0.08
    .Bytes
    0.08
     Hv
    0.07
     explosion
    0.07
     Norge
    0.07
     куб
    0.07
     Cube
    0.07
     hypers
    0.07
     домашних
    0.07
    Act Density 0.084%

    No Known Activations