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

    Neuronpedia

    INDEX
    Explanations

    common collocations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diagn
    0.47
     就是
    0.43
    })$;
    0.43
    Dequeue
    0.43
    分钟
    0.42
     مُ
    0.42
    ോ
    0.42
    يش
    0.41
    ]);
    0.41
     Vậy
    0.41
    POSITIVE LOGITS
     hobby
    0.55
     into
    0.54
     science
    0.53
     chopper
    0.51
     especially
    0.49
     cucumber
    0.49
     trying
    0.48
     reducing
    0.48
     di
    0.47
     overnight
    0.47
    Act Density 0.007%

    No Known Activations