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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Personally
    -0.07
     Psi
    -0.07
     Nir
    -0.07
    arium
    -0.06
     BF
    -0.06
    opolitan
    -0.06
    .bus
    -0.06
     příst
    -0.06
    ルク
    -0.06
    .defaultProps
    -0.06
    POSITIVE LOGITS
     valores
    0.07
     آزاد
    0.06
     север
    0.06
    DTO
    0.06
    zerbai
    0.06
     війни
    0.06
    Need
    0.06
    'une
    0.06
    Prices
    0.06
    redux
    0.06
    Act Density 0.001%

    No Known Activations