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

    Neuronpedia

    INDEX
    Explanations

    list conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outspoken
    0.77
    AssetDiscovery
    0.75
     realização
    0.74
     meditative
    0.73
     materialistic
    0.73
     oppressive
    0.71
     Vaccination
    0.70
     sobriety
    0.70
     Besoin
    0.69
     गर्नुहोस्
    0.69
    POSITIVE LOGITS
    和
    1.06
     и
    0.98
    ,
    0.97
    、
    0.95
    and
    0.94
     এবং
    0.92
     and
    0.90
    以及
    0.85
     और
    0.85
     आणि
    0.84
    Act Density 0.450%

    No Known Activations