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

    Neuronpedia

    INDEX
    Explanations

    introducing structured lists and sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ើរ
    0.40
     takže
    0.39
    所以在
    0.36
     disinfecting
    0.36
    かもしれませんが
    0.36
     ancients
    0.35
     fanatics
    0.35
     airliner
    0.35
     wikip
    0.34
    টিউট
    0.34
    POSITIVE LOGITS
     Emphasis
    0.69
     Each
    0.66
     Included
    0.66
     This
    0.62
     Alongside
    0.61
     Includes
    0.60
     Ultimately
    0.57
     Along
    0.57
    This
    0.56
    Each
    0.56
    Act Density 0.010%

    No Known Activations