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

    Neuronpedia

    INDEX
    Explanations

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plit
    -0.07
     parach
    -0.07
     Blender
    -0.07
     failures
    -0.07
    697
    -0.07
    828
    -0.06
     Thursday
    -0.06
     Another
    -0.06
    la
    -0.06
    合作
    -0.06
    POSITIVE LOGITS
     sense
    0.17
    sense
    0.15
     Sense
    0.15
    Sense
    0.14
     senses
    0.11
    ense
    0.09
     sensed
    0.09
     sensing
    0.09
     Dense
    0.08
     SSE
    0.08
    Act Density 0.024%

    No Known Activations