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

    Neuronpedia

    INDEX
    Explanations

    it's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikip
    0.49
     baron
    0.48
     fruit
    0.48
    合併
    0.48
     EMP
    0.47
     Fruit
    0.47
     PYTHON
    0.47
    ьев
    0.47
    нэ
    0.47
     Dawn
    0.46
    POSITIVE LOGITS
    p
    0.60
    g
    0.59
     enthält
    0.52
     rối
    0.51
    衄
    0.49
    i
    0.48
    pR
    0.48
    painter
    0.47
    inę
    0.46
    rients
    0.46
    Act Density 0.000%

    No Known Activations