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

    Neuronpedia

    INDEX
    Explanations

    colors or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    No
    0.82
     contrary
    0.78
    He
    0.74
    History
    0.73
     HISTORY
    0.68
     gladly
    0.68
    Very
    0.68
    Wind
    0.68
    }}
    0.68
    It
    0.67
    POSITIVE LOGITS
     facil
    0.82
    рон
    0.80
    യാണ്
    0.79
     nascent
    0.78
     infrast
    0.76
    presentasikan
    0.75
    quisitions
    0.72
     ಅಗ
    0.71
     facto
    0.71
    lomer
    0.71
    Act Density 0.002%

    No Known Activations