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

    Neuronpedia

    INDEX
    Explanations

    route definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الجسم
    0.41
     Jérôme
    0.39
     inhum
    0.38
    临床
    0.38
    bapt
    0.37
     آنچه
    0.36
     jednog
    0.36
    viel
    0.36
    ھر
    0.35
     Kamen
    0.35
    POSITIVE LOGITS
    ?),
    0.59
    '),
    0.55
     ''),
    0.49
    !),
    0.48
    ...),
    0.47
    include
    0.47
     ""),
    0.46
    adigan
    0.45
    ),
    0.44
     '=',
    0.44
    Act Density 0.001%

    No Known Activations