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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    假
    -0.07
    968
    -0.06
    참
    -0.06
    يمي
    -0.06
    ीज
    -0.06
    .Does
    -0.06
    .D
    -0.06
    DEC
    -0.06
    ержав
    -0.06
    present
    -0.06
    POSITIVE LOGITS
     broadly
    0.07
     Oculus
    0.07
     clicks
    0.06
     extensively
    0.06
     hop
    0.06
     exped
    0.06
     intersections
    0.06
     Hyper
    0.06
    _annotation
    0.06
     Encoding
    0.06
    Act Density 0.002%

    No Known Activations