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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sad
    -0.07
    ขณะท
    -0.07
     GIF
    -0.06
     regained
    -0.06
    /sl
    -0.06
     puppies
    -0.06
    '],↵
    -0.06
    ющей
    -0.06
     可
    -0.06
    Factors
    -0.06
    POSITIVE LOGITS
     maman
    0.07
     provinc
    0.06
    sport
    0.06
     домов
    0.06
    ier
    0.06
    ائلة
    0.06
    IER
    0.06
     kill
    0.06
     enfermed
    0.06
    +lsi
    0.06
    Act Density 0.093%

    No Known Activations