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

    Neuronpedia

    INDEX
    Explanations

    gravity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inin
    -0.06
     Ikea
    -0.06
    roup
    -0.06
    Ф
    -0.06
     Ui
    -0.06
    -digit
    -0.06
     FOUR
    -0.06
    Woman
    -0.06
    OLUME
    -0.06
     IPs
    -0.06
    POSITIVE LOGITS
     огранич
    0.07
     Durham
    0.07
     forbid
    0.07
    -multi
    0.07
    ><?=$
    0.07
     дорож
    0.07
     academia
    0.06
    "%(
    0.06
     vš
    0.06
     khắc
    0.06
    Act Density 0.001%

    No Known Activations