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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bí
    -0.08
    仙境
    -0.07
     onNext
    -0.07
     Reserve
    -0.07
    잨
    -0.07
    /icons
    -0.07
    んですね
    -0.07
     verificar
    -0.07
    蛐
    -0.07
    .year
    -0.07
    POSITIVE LOGITS
    ˢ
    0.08
    她们
    0.07
     ¬
    0.07
     Carr
    0.07
     Deletes
    0.07
     Dal
    0.07
    搬到
    0.07
    _quad
    0.07
     retail
    0.07
    Closing
    0.06
    Act Density 0.017%

    No Known Activations