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

    Neuronpedia

    INDEX
    Explanations

    honeys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permettant
    0.48
    鯽
    0.47
    चे
    0.46
    ंपर्यंत
    0.46
     aplatis
    0.45
     recognising
    0.45
    允許
    0.45
    愊
    0.45
     événement
    0.44
     ~(~)
    0.43
    POSITIVE LOGITS
    pple
    0.45
    imb
    0.45
    cpu
    0.45
    topLeft
    0.45
     =
    0.44
    install
    0.44
    _
    0.44
     +
    0.43
     puan
    0.43
    oning
    0.43
    Act Density 0.001%

    No Known Activations