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

    Neuronpedia

    INDEX
    Explanations

    releg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Selena
    -0.08
     Blvd
    -0.08
     réflexion
    -0.07
     overt
    -0.07
     Bakery
    -0.07
     Glue
    -0.07
     iler
    -0.07
     отраж
    -0.07
     عليه
    -0.07
    炼
    -0.07
    POSITIVE LOGITS
     rampant
    0.08
    0.08
    (content
    0.08
    switch
    0.08
     curse
    0.07
    ს
    0.07
    (({
    0.07
     clubs
    0.07
     pob
    0.07
    ('.
    0.07
    Act Density 0.002%
    No Known Activations