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

    Neuronpedia

    INDEX
    Explanations

    code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conting
    -0.07
    ecko
    -0.07
    itesse
    -0.07
    unde
    -0.06
    :frame
    -0.06
     fet
    -0.06
    precated
    -0.06
     соз
    -0.06
    enh
    -0.06
     JFK
    -0.06
    POSITIVE LOGITS
    ování
    0.07
    пи
    0.06
     ล
    0.06
    Modules
    0.06
    括
    0.06
     centroid
    0.06
    ujte
    0.06
     votre
    0.06
    .interface
    0.06
    .getConfig
    0.06
    Act Density 0.001%

    No Known Activations