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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skiing
    -0.07
    .expression
    -0.07
     intensive
    -0.07
    Attention
    -0.07
     tiger
    -0.06
    .EntityManager
    -0.06
    薦
    -0.06
    ☴
    -0.06
    .WARNING
    -0.06
    adece
    -0.06
    POSITIVE LOGITS
     code
    0.09
    _SCL
    0.06
    	O
    0.06
     imply
    0.06
    であり
    0.06
     Killed
    0.06
    劃
    0.06
    .ASCII
    0.06
    -written
    0.06
     vary
    0.06
    Act Density 0.019%

    No Known Activations