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

    Neuronpedia

    INDEX
    Explanations

    years, events, second occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     epidemics
    0.33
     multiplets
    0.33
     vertebrates
    0.32
     campagnes
    0.31
     logiciels
    0.31
     valeur
    0.29
     competitions
    0.29
    ിലുള്ള
    0.29
     Senhor
    0.28
     grafo
    0.28
    POSITIVE LOGITS
     infamous
    0.35
    聽
    0.32
     audacious
    0.30
    tiktok
    0.29
     Affordable
    0.28
     elde
    0.28
     Oscars
    0.28
    瑯
    0.28
     IPCC
    0.28
     tuvimos
    0.28
    Act Density 0.052%

    No Known Activations