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

    Neuronpedia

    INDEX
    Explanations

    data, numbers, metrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Queue
    -0.07
    萬
    -0.07
    .children
    -0.06
     door
    -0.06
    	current
    -0.06
    (old
    -0.06
     carriage
    -0.06
     Carb
    -0.06
     orden
    -0.06
     anxiety
    -0.06
    POSITIVE LOGITS
    .aggregate
    0.07
     تح
    0.07
     GE
    0.06
    .',
↵
    0.06
    běhu
    0.06
    .identity
    0.06
     údajů
    0.06
    .PI
    0.06
    FP
    0.06
     Seç
    0.06
    Act Density 0.129%

    No Known Activations