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

    Neuronpedia

    INDEX
    Explanations

    identifying specific characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notoriously
    0.47
    HandleFunc
    0.47
    Ich
    0.46
     painfully
    0.44
    Datei
    0.43
    Michael
    0.42
    Luke
    0.42
     மோச
    0.42
    和小
    0.42
    Ricardo
    0.41
    POSITIVE LOGITS
     exemptions
    0.50
     services
    0.48
     tailgate
    0.47
     goods
    0.47
     camping
    0.46
     vaccinations
    0.45
    urcharge
    0.44
     registrations
    0.43
    antaranya
    0.43
     Balkans
    0.43
    Act Density 0.001%

    No Known Activations