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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ế
    -0.07
    .paths
    -0.07
    -ver
    -0.06
    یری
    -0.06
     тут
    -0.06
    buz
    -0.06
    oled
    -0.06
    เอ
    -0.06
     Sentry
    -0.06
    สภ
    -0.06
    POSITIVE LOGITS
     herk
    0.07
    fft
    0.07
     Ros
    0.06
     cooperative
    0.06
     monstrous
    0.06
    293
    0.06
    781
    0.06
     Observatory
    0.06
    698
    0.06
    091
    0.06
    Act Density 0.000%

    No Known Activations