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

    Neuronpedia

    INDEX
    Explanations

    awkward or original phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mecanismos
    0.52
    owler
    0.50
     curiously
    0.49
     computeEncoder
    0.48
     enzimas
    0.46
    你們
    0.45
     presume
    0.45
     இதை
    0.44
     μεγαλ
    0.44
     jeopardize
    0.44
    POSITIVE LOGITS
    ਾ
    0.49
     ajal
    0.49
    ้า
    0.48
     permission
    0.47
     tonal
    0.45
    fors
    0.44
    وفر
    0.44
    Pets
    0.43
     okolo
    0.42
     permissions
    0.42
    Act Density 0.000%

    No Known Activations