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

    Neuronpedia

    INDEX
    Explanations

    black and white

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    phia
    0.87
    𝘣
    0.85
    𝘴
    0.84
     fluke
    0.83
     Seek
    0.83
    程度
    0.83
    ফান
    0.82
     Rooms
    0.81
    гация
    0.81
    extent
    0.81
    POSITIVE LOGITS
    smith
    1.22
    outs
    1.22
    list
    1.21
     friday
    1.13
    listed
    1.13
    listing
    1.11
    ening
    1.08
     soot
    1.07
    listView
    1.07
    thorn
    1.04
    Act Density 0.057%

    No Known Activations