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

    Neuronpedia

    INDEX
    Explanations

    code execution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colo
    -0.08
     yay
    -0.07
    oland
    -0.07
     mater
    -0.07
    aso
    -0.07
    🔢
    -0.07
    有兴趣
    -0.07
     Monster
    -0.07
     máximo
    -0.07
     slower
    -0.07
    POSITIVE LOGITS
    science
    0.07
    (each
    0.07
    펙
    0.07
     gentle
    0.07
    荫
    0.07
    (raw
    0.07
     fluorescent
    0.06
    겼
    0.06
    (Get
    0.06
    	rep
    0.06
    Act Density 0.025%

    No Known Activations