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

    Neuronpedia

    INDEX
    Explanations

    open and honest communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    支援
    0.43
     frantic
    0.40
     photovoltaic
    0.40
     tuples
    0.39
     Vid
    0.38
     nginx
    0.38
     motivation
    0.38
     PV
    0.38
     enticing
    0.38
    眺
    0.37
    POSITIVE LOGITS
     honest
    0.80
    honest
    0.73
     honesty
    0.71
     truthful
    0.68
     truthfully
    0.67
     openly
    0.67
     Honest
    0.66
     unpopular
    0.65
     vérit
    0.64
    实话
    0.63
    Act Density 0.123%

    No Known Activations