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

    Neuronpedia

    INDEX
    Explanations

    code and markups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stub
    -0.07
     Spatial
    -0.07
    /M
    -0.07
     penalty
    -0.07
    RED
    -0.06
    図
    -0.06
    .ch
    -0.06
     contraction
    -0.06
     Bailey
    -0.06
    sse
    -0.06
    POSITIVE LOGITS
    ufacturer
    0.06
    Permanent
    0.06
    병
    0.06
    (epoch
    0.06
    そして
    0.06
    iveau
    0.06
    _google
    0.06
     pinpoint
    0.06
    ीद
    0.06
     Rockies
    0.06
    Act Density 0.008%

    No Known Activations