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

    Neuronpedia

    INDEX
    Explanations

    BERT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Tile
    -0.06
    Cleanup
    -0.06
    tpl
    -0.06
    flip
    -0.06
    _mpi
    -0.06
     tzv
    -0.06
    _imm
    -0.06
     Charger
    -0.06
    achte
    -0.06
     вплив
    -0.06
    POSITIVE LOGITS
     regimen
    0.07
    esinin
    0.07
     RI
    0.07
     emotionally
    0.07
    ERT
    0.07
     GV
    0.07
     sess
    0.07
     treatments
    0.07
     zů
    0.06
     Rosie
    0.06
    Act Density 0.002%

    No Known Activations