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

    Neuronpedia

    INDEX
    Explanations

    I can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     must
    0.90
    Must
    0.88
    must
    0.86
    thur
    0.73
     Must
    0.72
    /*
    0.72
    levant
    0.72
    TH
    0.71
    ‒
    0.70
    TE
    0.66
    POSITIVE LOGITS
     주세요
    1.00
     특징
    0.98
     specialise
    0.89
     eignet
    0.87
     unsere
    0.87
     our
    0.87
     שלנו
    0.86
     사용하는
    0.85
     specializes
    0.85
    我們的
    0.85
    Act Density 0.123%

    No Known Activations