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

    Neuronpedia

    INDEX
    Explanations

    Legal and insurance contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Commissioner
    -0.07
     dyst
    -0.07
    匀
    -0.07
     tussen
    -0.07
    اسر
    -0.07
     Arch
    -0.07
    uş
    -0.06
     Sponsor
    -0.06
    campo
    -0.06
    Sy
    -0.06
    POSITIVE LOGITS
    ⠀⠀
    0.08
    DCALL
    0.07
    こんに
    0.07
    ..........
    0.07
    能够在
    0.06
    📛
    0.06
    reader
    0.06
    üncü
    0.06
    ########
    0.06
     Japanese
    0.06
    Act Density 0.026%

    No Known Activations