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

    Neuronpedia

    INDEX
    Explanations

    Scientific and mathematical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     précieux
    -0.08
     sensed
    -0.08
     osm
    -0.08
     hashed
    -0.07
     menn
    -0.07
     kvinner
    -0.07
     csv
    -0.07
    邮
    -0.07
    ווי
    -0.07
    Reviewed
    -0.07
    POSITIVE LOGITS
     sustaining
    0.12
     Sustain
    0.11
     sustain
    0.11
     contagious
    0.11
     sustained
    0.11
    _chain
    0.11
     Sust
    0.11
     contag
    0.11
    Cascade
    0.10
    Propagation
    0.10
    Act Density 0.019%

    No Known Activations