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

    Neuronpedia

    INDEX
    Explanations

    political campaigns, alter large

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     figurine
    0.47
     paddock
    0.47
    ウェイ
    0.46
     deterrent
    0.45
     চার্জ
    0.45
    ແມ່ນ
    0.45
     cách
    0.44
     chaired
    0.43
    TouchUpInside
    0.42
     변경
    0.42
    POSITIVE LOGITS
    elv
    0.47
    рова
    0.43
     shading
    0.43
     EMPTY
    0.43
    Cb
    0.42
    䆔
    0.42
    巴
    0.41
    Mq
    0.41
     ಅದೇ
    0.41
     তত্ব
    0.40
    Act Density 0.000%

    No Known Activations