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

    Neuronpedia

    INDEX
    Explanations

    Coding imports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dictionary
    -0.07
    \Requests
    -0.07
     pores
    -0.07
    刬
    -0.07
    印章
    -0.07
    ock
    -0.07
     bos
    -0.06
    self
    -0.06
    _birth
    -0.06
    RGB
    -0.06
    POSITIVE LOGITS
    ).[
    0.07
    ┮
    0.07
     muốn
    0.06
     đều
    0.06
    创造了
    0.06
    .setName
    0.06
     gratuito
    0.06
    #####
    0.06
    ٬
    0.06
    逛
    0.06
    Act Density 0.001%

    No Known Activations