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

    Neuronpedia

    INDEX
    Explanations

    wired Ethernet, naming convention, see object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    two
    0.49
    ин
    0.46
     Jesús
    0.44
     أحمد
    0.43
    cienza
    0.43
    سي
    0.43
    ジェ
    0.43
    વ
    0.42
    ジョ
    0.42
     apoyar
    0.42
    POSITIVE LOGITS
     Oats
    0.49
     अच्छ
    0.47
    ös
    0.46
    setMaximum
    0.45
     nonsense
    0.45
     oats
    0.45
    itik
    0.44
    ounds
    0.44
     accur
    0.43
     kaos
    0.43
    Act Density 0.000%

    No Known Activations