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

    Neuronpedia

    INDEX
    Explanations

    difficulty letting go

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Share
    0.51
    CEPTION
    0.51
    BackgroundHelper
    0.48
    ception
    0.48
     ডিসেম্বর
    0.46
    XYGEN
    0.45
     Rom
    0.45
    Assets
    0.45
    Underwater
    0.45
     somit
    0.44
    POSITIVE LOGITS
     n
    0.50
     cinci
    0.46
     enumerate
    0.45
    illeri
    0.45
    ēng
    0.44
     inds
    0.44
     enumerated
    0.43
     template
    0.42
     разум
    0.42
     accustomed
    0.41
    Act Density 0.003%

    No Known Activations