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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ROOM
    -0.07
     bj
    -0.07
    γκ
    -0.07
    FILE
    -0.06
    ueur
    -0.06
    َر
    -0.06
     شهید
    -0.06
    -carousel
    -0.06
    Updated
    -0.06
    需
    -0.06
    POSITIVE LOGITS
     their
    0.09
     theirs
    0.06
     themselves
    0.06
    openssl
    0.06
     önemli
    0.06
     เว
    0.06
     intended
    0.06
     ROLE
    0.06
     Its
    0.06
    their
    0.06
    Act Density 0.114%

    No Known Activations