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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лю
    -0.07
     Presence
    -0.06
     enzym
    -0.06
     Appliances
    -0.06
    류
    -0.06
    destroy
    -0.06
    ंपर
    -0.06
    inin
    -0.06
    Trees
    -0.06
    انی
    -0.06
    POSITIVE LOGITS
    .Real
    0.07
    援
    0.07
    groupBox
    0.07
    .Head
    0.07
     informant
    0.06
     铁
    0.06
     Fort
    0.06
     churn
    0.06
    .intValue
    0.06
     рух
    0.06
    Act Density 0.010%

    No Known Activations