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

    Neuronpedia

    INDEX
    Explanations

    Mirrors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tail
    -0.08
     download
    -0.07
     EPA
    -0.07
    .orange
    -0.07
     uyg
    -0.07
    onomia
    -0.07
    izações
    -0.07
    izaciones
    -0.07
     whistle
    -0.07
    .download
    -0.07
    POSITIVE LOGITS
     selfie
    0.13
     зеркало
    0.11
     narciss
    0.10
     miroir
    0.10
     зерк
    0.10
     gaze
    0.10
     ಕನ್ನಡ
    0.10
    自拍
    0.09
    /self
    0.09
     viewer
    0.09
    Act Density 0.032%

    No Known Activations