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

    Neuronpedia

    INDEX
    Explanations

    online resources and communities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Precio
    0.23
    靡
    0.22
    ։
    0.22
    Arch
    0.22
    Pt
    0.22
    Elephant
    0.22
    專
    0.21
     eenvoud
    0.21
    Nft
    0.21
     (£
    0.21
    POSITIVE LOGITS
     Yose
    0.23
     Australian
    0.20
     색
    0.20
     A
    0.20
     labeled
    0.20
    adka
    0.20
     nghi
    0.20
     മണ്ണി
    0.20
     Isabella
    0.19
     posle
    0.19
    Act Density 0.000%

    No Known Activations