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

    Neuronpedia

    INDEX
    Explanations

    domain knowledge interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    calculations
    0.49
    funciones
    0.45
     calculations
    0.43
     booze
    0.43
     heartache
    0.43
     allotments
    0.41
     fiberglass
    0.40
     heartbreak
    0.40
     racked
    0.40
     speedy
    0.40
    POSITIVE LOGITS
     domain
    0.86
     Domain
    0.79
     Semantic
    0.76
    Domain
    0.71
    domain
    0.70
     provenance
    0.70
     ontology
    0.69
     subgoal
    0.68
     contextual
    0.67
     instantiated
    0.67
    Act Density 0.042%

    No Known Activations