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

    Neuronpedia

    INDEX
    Explanations

    driver instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trip
    -0.07
     password
    -0.07
    genes
    -0.07
     Ari
    -0.06
    uales
    -0.06
    emails
    -0.06
     Wallace
    -0.06
    PRIVATE
    -0.06
    "#
    -0.06
     sequences
    -0.06
    POSITIVE LOGITS
    óg
    0.07
     활용
    0.06
    IZE
    0.06
     siyasi
    0.06
    _mpi
    0.06
     mont
    0.06
     складі
    0.06
    ント
    0.06
     nhận
    0.06
    _MULT
    0.06
    Act Density 0.050%

    No Known Activations