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

    Neuronpedia

    INDEX
    Explanations

    composition art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    召开
    -0.08
     lasted
    -0.08
     charging
    -0.08
     안전
    -0.07
    озможно
    -0.07
     bảo
    -0.07
     armazen
    -0.07
     DES
    -0.07
    纪律
    -0.07
    .ALIGN
    -0.07
    POSITIVE LOGITS
    Layers
    0.10
     ಹಿನ್ನೆ
    0.09
     collage
    0.09
     hinten
    0.09
     Layers
    0.09
     layers
    0.09
     الخلف
    0.09
     layering
    0.08
     backdrop
    0.08
    _layers
    0.08
    Act Density 0.007%

    No Known Activations