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

    Neuronpedia

    INDEX
    Explanations

    scientific explanations and jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ро
    0.85
    ან
    0.80
     Ро
    0.80
    Ins
    0.77
    اد
    0.77
     Computers
    0.77
    cito
    0.77
    IMA
    0.76
     Cardi
    0.75
     او
    0.75
    POSITIVE LOGITS
    ны
    0.97
    ievement
    0.94
    ர்ஸ்
    0.91
    टीएस
    0.87
     particulate
    0.85
     SCIENCE
    0.85
    getClassName
    0.84
    rstrip
    0.82
     science
    0.82
    ENGTH
    0.82
    Act Density 0.074%

    No Known Activations