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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bild
    -0.07
     complexion
    -0.07
     picture
    -0.06
     Vel
    -0.06
     Chat
    -0.06
     servicios
    -0.06
    这一
    -0.06
    endez
    -0.06
    ('//
    -0.06
    宜
    -0.06
    POSITIVE LOGITS
     harms
    0.07
     somew
    0.07
    .Π
    0.06
    .')↵↵
    0.06
     Kr
    0.06
    ract
    0.06
     NRL
    0.06
    qh
    0.06
    .act
    0.06
    무
    0.06
    Act Density 0.025%

    No Known Activations