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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offences
    -0.07
    學
    -0.07
     hảo
    -0.07
    constraint
    -0.07
     retire
    -0.07
    orie
    -0.07
    hangi
    -0.06
    .IsNotNull
    -0.06
     dividend
    -0.06
    举
    -0.06
    POSITIVE LOGITS
     Adidas
    0.06
     Pom
    0.06
    raní
    0.06
    ροφορ
    0.06
     onOptionsItemSelected
    0.06
     getProperty
    0.06
    ustria
    0.06
    。<
    0.06
     gala
    0.06
     advertis
    0.06
    Act Density 0.126%

    No Known Activations