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

    Neuronpedia

    INDEX
    Explanations

    types, options, styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    テ
    0.46
    ต้น
    0.46
     DAN
    0.45
    थ
    0.44
     macron
    0.43
     CDK
    0.43
    取る
    0.43
    테
    0.42
     preko
    0.42
     gastroenter
    0.42
    POSITIVE LOGITS
    Fern
    0.51
     ఎన్నిక
    0.46
    ｍｍ
    0.45
    -‘
    0.43
    πάρχ
    0.42
    fühl
    0.42
    訲
    0.42
    öp
    0.42
    дна
    0.41
    gments
    0.41
    Act Density 0.001%

    No Known Activations