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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interest
    -0.07
    ":"","
    -0.06
     Covenant
    -0.06
     अपर
    -0.06
    容易
    -0.06
    Submit
    -0.06
    Linux
    -0.06
    UInt
    -0.06
     исч
    -0.06
     欧美
    -0.06
    POSITIVE LOGITS
    ublished
    0.07
     magician
    0.06
     attached
    0.06
     distracted
    0.06
    etical
    0.06
    同意
    0.06
    *>
    0.06
    대
    0.06
    edImage
    0.06
     읽
    0.06
    Act Density 0.110%

    No Known Activations