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

    Neuronpedia

    INDEX
    Explanations

    product description and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Desenvolvimento
    0.43
     assuntos
    0.40
     embaixo
    0.40
    畈
    0.39
     reeks
    0.39
    Појединачна
    0.38
     comportement
    0.38
     ří
    0.38
     Dernière
    0.38
     Développement
    0.38
    POSITIVE LOGITS
    Wallace
    0.46
    className
    0.43
     परिचय
    0.42
    crs
    0.41
     Wallace
    0.41
    ukaemia
    0.38
    zub
    0.38
    designer
    0.38
    roga
    0.38
    젝
    0.38
    Act Density 0.000%

    No Known Activations