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

    Neuronpedia

    INDEX
    Explanations

    fig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pad
    -0.07
    ieten
    -0.07
     Econom
    -0.07
     tipped
    -0.06
     down
    -0.06
     soul
    -0.06
     Panda
    -0.06
     numberWith
    -0.06
     blossom
    -0.06
    instead
    -0.06
    POSITIVE LOGITS
    ุส
    0.07
    ]</
    0.07
    (fig
    0.07
     นาง
    0.06
     Confeder
    0.06
     Dig
    0.06
     intra
    0.06
    ----------</
    0.06
    ์
    0.06
    À
    0.06
    Act Density 0.002%

    No Known Activations