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

    Neuronpedia

    INDEX
    Explanations

    the patient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ă
    0.37
     vecchio
    0.34
     frü
    0.33
     drie
    0.33
     étaient
    0.32
    是
    0.32
     dari
    0.31
     einiger
    0.31
     ešte
    0.30
    い
    0.30
    POSITIVE LOGITS
     Organizations
    0.29
     SWOT
    0.29
    ↵
    0.28
     activism
    0.28
     decentral
    0.27
     paramilitary
    0.27
     SWAT
    0.27
     TV
    0.26
     Industry
    0.26
     logistical
    0.26
    Act Density 1.688%

    No Known Activations