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

    Neuronpedia

    INDEX
    Explanations

    origins and history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seva
    -0.08
    ulnerability
    -0.08
     thrott
    -0.08
    countries
    -0.08
     tragedies
    -0.08
     hü
    -0.08
    的是
    -0.07
    (ev
    -0.07
    followers
    -0.07
    grees
    -0.07
    POSITIVE LOGITS
     earliest
    0.12
     dated
    0.09
    早
    0.09
     temprano
    0.08
     найден
    0.08
     datant
    0.08
    Recorded
    0.08
    Annotated
    0.08
     documented
    0.08
    Early
    0.08
    Act Density 0.021%

    No Known Activations