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

    Neuronpedia

    INDEX
    Explanations

    TH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uga
    -0.07
     inde
    -0.07
    antis
    -0.07
    datatype
    -0.07
     açısından
    -0.07
    ads
    -0.07
     Bod
    -0.07
     Bit
    -0.07
     dışı
    -0.06
    앝
    -0.06
    POSITIVE LOGITS
    LANGUAGE
    0.07
     />)↵
    0.07
    _DESC
    0.07
     UILabel
    0.07
    throw
    0.07
    low
    0.07
    QUE
    0.07
    强烈
    0.07
    �
    0.06
     Caleb
    0.06
    Act Density 0.000%

    No Known Activations