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

    Neuronpedia

    INDEX
    Explanations

    riding a horse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >>>
    0.40
    implicitly
    0.40
     ပဲ
    0.40
     ö
    0.38
     extranjeros
    0.38
     Besançon
    0.37
     ssh
    0.37
     palav
    0.36
    Օ
    0.36
     ناخد
    0.36
    POSITIVE LOGITS
    Holly
    0.43
     Processing
    0.42
    Pearson
    0.41
     pathways
    0.40
     *}$
    0.40
    photon
    0.40
    insulin
    0.39
     changes
    0.39
    ्रीन
    0.38
     rigidity
    0.38
    Act Density 0.002%

    No Known Activations