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

    Neuronpedia

    INDEX
    Explanations

    research methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     such
    0.43
     rápidamente
    0.42
     recombinant
    0.40
    得以
    0.40
     mitigating
    0.39
     integrable
    0.39
    τ
    0.39
     hypergeometric
    0.38
     immediately
    0.38
     uncomfortable
    0.38
    POSITIVE LOGITS
     acres
    0.46
     അറിയ
    0.43
     tileSize
    0.42
    lik
    0.42
     étages
    0.42
     étoiles
    0.39
     Анато
    0.39
     pagamento
    0.39
     regol
    0.38
    একে
    0.38
    Act Density 0.000%

    No Known Activations