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

    Neuronpedia

    INDEX
    Explanations

    sparked your excitement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ፣
    0.55
     enemy
    0.52
     armor
    0.50
    ॅमिली
    0.46
     dessin
    0.46
     dessert
    0.45
     faucets
    0.45
    𝙔
    0.44
    因為
    0.44
     цветов
    0.44
    POSITIVE LOGITS
    Counc
    0.59
    DA
    0.54
    nier
    0.54
    AF
    0.51
    Acetyl
    0.50
    ش
    0.50
    nof
    0.49
    ingly
    0.48
    да
    0.47
    Ala
    0.47
    Act Density 0.632%

    No Known Activations