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

    Neuronpedia

    INDEX
    Explanations

    antibody-related texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Evil
    -0.07
     pride
    -0.07
     Dough
    -0.07
     Sonic
    -0.07
    Saved
    -0.06
    rání
    -0.06
    	z
    -0.06
     furnishings
    -0.06
    адж
    -0.06
     lightning
    -0.06
    POSITIVE LOGITS
     adequate
    0.07
    医
    0.07
     кас
    0.06
     pracy
    0.06
     onCancel
    0.06
    	Toast
    0.06
    ])){↵
    0.06
    }",↵
    0.06
    Để
    0.06
    .statistics
    0.06
    Act Density 0.012%

    No Known Activations