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

    Neuronpedia

    INDEX
    Explanations

    selection of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    פים
    1.21
     exib
    1.19
     言っ
    1.19
     सांगित
    1.16
    ⿷
    1.10
     espèce
    1.09
     méthod
    1.09
    Chemistry
    1.08
    Ổ
    1.07
    𝖊
    1.07
    POSITIVE LOGITS
     putri
    1.14
     unpopular
    1.10
    не
    1.09
    нето
    1.08
    ли
    1.07
    нее
    1.05
     cutting
    1.01
    rho
    1.01
    pronged
    1.00
     troubled
    1.00
    Act Density 0.000%

    No Known Activations