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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arch
    -0.07
    gado
    -0.07
    ям
    -0.07
     succeeding
    -0.07
    outputs
    -0.06
    탁
    -0.06
    .setMaximum
    -0.06
     skipping
    -0.06
     �
    -0.06
    	for
    -0.06
    POSITIVE LOGITS
    ैं.↵
    0.06
     lille
    0.06
    ۱۳۹
    0.06
    .`
    0.06
    fono
    0.06
     Tags
    0.06
    ヴィ
    0.06
    ”.↵
    0.06
    Jon
    0.06
    ponential
    0.06
    Act Density 0.019%

    No Known Activations