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

    Neuronpedia

    INDEX
    Explanations

    .auth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ingles
    -0.07
    _li
    -0.06
    ）（
    -0.06
     Huff
    -0.06
     Coco
    -0.06
    quiv
    -0.06
    (Room
    -0.06
    -plane
    -0.06
     arises
    -0.06
     Chim
    -0.06
    POSITIVE LOGITS
     Α
    0.07
    ()",
    0.07
     stall
    0.07
    OLER
    0.07
    گاه
    0.06
     scheduler
    0.06
     code
    0.06
    arguments
    0.06
     ماند
    0.06
     endorsement
    0.06
    Act Density 0.002%

    No Known Activations