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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     result
    -0.08
     participants
    -0.07
     status
    -0.07
     dié
    -0.07
    aceous
    -0.07
     creative
    -0.07
    pcb
    -0.07
     feasible
    -0.07
     Direction
    -0.07
     frequency
    -0.07
    POSITIVE LOGITS
     poorer
    0.09
    ->____
    0.09
     hers
    0.09
     wors
    0.08
    (Note
    0.08
     кис
    0.08
     fors
    0.08
     steigen
    0.08
    ("_
    0.08
     парла
    0.08
    Act Density 0.019%

    No Known Activations