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

    Neuronpedia

    INDEX
    Explanations

    specific entities and their properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Culture
    0.47
    Buddy
    0.47
    Tools
    0.45
     الع
    0.45
    Dragon
    0.44
    Wolf
    0.43
    Connector
    0.43
    Fest
    0.42
    ።
    0.42
     جدید
    0.42
    POSITIVE LOGITS
    estimates
    0.49
     corroborated
    0.48
     outperform
    0.48
     subpopulations
    0.47
     superior
    0.46
     broader
    0.46
     corrobor
    0.46
     anecdotal
    0.43
     insightful
    0.42
     outperforms
    0.42
    Act Density 0.002%

    No Known Activations