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

    Neuronpedia

    INDEX
    Explanations

    introductions to descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terus
    0.52
     products
    0.47
     gaskets
    0.47
     because
    0.46
     refills
    0.46
     gacche
    0.45
     wording
    0.44
     towar
    0.44
     where
    0.44
     stvari
    0.44
    POSITIVE LOGITS
     elegant
    0.78
     intriguing
    0.70
     unassuming
    0.68
     fascinating
    0.67
     robuste
    0.66
     elegante
    0.66
     impressive
    0.65
     innovative
    0.64
     insightful
    0.63
     enigmatic
    0.63
    Act Density 0.061%

    No Known Activations