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

    Neuronpedia

    INDEX
    Explanations

    open weights model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [{\
    0.40
     McKee
    0.40
    堤
    0.39
    ées
    0.39
    ubes
    0.38
    нтип
    0.38
     chin
    0.38
    getResources
    0.38
    okit
    0.37
    真心
    0.37
    POSITIVE LOGITS
     Working
    0.68
     Feather
    0.59
     Wid
    0.58
    Working
    0.52
     Barrow
    0.52
     WORKING
    0.52
     Leigh
    0.52
     Sidd
    0.49
    Wid
    0.48
    WORKING
    0.48
    Act Density 0.002%

    No Known Activations