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

    Neuronpedia

    INDEX
    Explanations

    understand and offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.77
     manufacturer
    0.69
    璁
    0.68
     supplier
    0.65
     bird
    0.65
    ទេស
    0.64
     love
    0.62
    msup
    0.62
     hamster
    0.61
    raphene
    0.60
    POSITIVE LOGITS
    Entre
    0.82
    Indeed
    0.80
     وسي
    0.78
    Anything
    0.77
     കോണ്‍
    0.77
    任何人
    0.77
    Driving
    0.76
    可能會
    0.76
    തില്‍
    0.75
    ANY
    0.75
    Act Density 0.000%

    No Known Activations