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

    Neuronpedia

    INDEX
    Explanations

    advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isans
    -0.09
    saus
    -0.09
    .invoice
    -0.09
    (invoice
    -0.09
     Manufacturers
    -0.08
    criptions
    -0.08
    alloween
    -0.08
     mooiste
    -0.08
     отмет
    -0.08
    sku
    -0.08
    POSITIVE LOGITS
     ಸಲ
    0.08
     terrestrial
    0.08
     sympathetic
    0.07
     try
    0.07
     proporcion
    0.07
    Try
    0.07
     deng
    0.07
     diplomatic
    0.07
     preventive
    0.07
     last
    0.07
    Act Density 0.034%

    No Known Activations