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

    Neuronpedia

    INDEX
    Explanations

    extracts or classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Biden
    0.46
     classmates
    0.46
    ৈত্র
    0.45
    BJP
    0.44
    érées
    0.44
    গল
    0.42
     mieszkań
    0.42
    Putin
    0.42
    Ger
    0.42
    вича
    0.42
    POSITIVE LOGITS
    ijski
    0.44
    rout
    0.43
    XT
    0.41
     XT
    0.41
    xt
    0.41
     Community
    0.40
    pth
    0.40
     unicorn
    0.39
     Univers
    0.39
    its
    0.39
    Act Density 0.006%

    No Known Activations