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

    Neuronpedia

    INDEX
    Explanations

    lists, organizations and items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igin
    -0.08
     Pasta
    -0.07
    ,array
    -0.06
    nota
    -0.06
     watt
    -0.06
     Darth
    -0.06
    推荐
    -0.06
     formatter
    -0.06
    King
    -0.06
     велик
    -0.06
    POSITIVE LOGITS
     movimiento
    0.06
    uteur
    0.06
    urrection
    0.06
     Morrow
    0.06
    ição
    0.06
    .ec
    0.06
    .Meta
    0.06
    	ss
    0.06
     yi
    0.06
    xdb
    0.06
    Act Density 0.159%

    No Known Activations