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

    Neuronpedia

    INDEX
    Explanations

    building or creating something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SI
    0.81
    SA
    0.77
    SE
    0.73
    SS
    0.70
    c
    0.68
    SK
    0.63
    SES
    0.63
    DNA
    0.63
    CA
    0.62
    to
    0.61
    POSITIVE LOGITS
     construct
    0.95
     конструк
    0.94
     costruire
    0.90
     соору
    0.84
     constructions
    0.82
     konstru
    0.81
     konstruk
    0.81
     건설
    0.80
     Construct
    0.80
    构造
    0.79
    Act Density 0.041%

    No Known Activations