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

    Neuronpedia

    INDEX
    Explanations

    science and knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weighted
    -0.07
    """
↵
↵
    -0.07
    ynamo
    -0.07
     חופשי
    -0.07
    变现
    -0.07
     magical
    -0.07
    -0.07
    筒
    -0.06
    .swagger
    -0.06
    -0.06
    POSITIVE LOGITS
    ﾐ
    0.08
     cocina
    0.07
    .Year
    0.07
    ellidos
    0.07
     getNext
    0.07
     Coc
    0.06
    ıldığı
    0.06
    🍤
    0.06
    ić
    0.06
     Colombian
    0.06
    Act Density 0.083%

    No Known Activations