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

    Neuronpedia

    INDEX
    Explanations

    #define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _phr
    -0.07
     cris
    -0.07
     Render
    -0.07
     ponds
    -0.07
    ring
    -0.06
     Besides
    -0.06
    yas
    -0.06
    اقتص
    -0.06
     vidé
    -0.06
     Dress
    -0.06
    POSITIVE LOGITS
    exampleInput
    0.07
     escalating
    0.06
    .cover
    0.06
    ienen
    0.06
     VIDEO
    0.06
    ，就
    0.06
    عداد
    0.06
     MN
    0.06
    '´
    0.06
     impartial
    0.06
    Act Density 0.009%

    No Known Activations