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

    Neuronpedia

    INDEX
    Explanations

    behavior and biometrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rule
    -0.08
    IPP
    -0.08
    printed
    -0.08
    āj
    -0.08
    armen
    -0.07
     paso
    -0.07
    ponsor
    -0.07
    PAIR
    -0.07
    -cle
    -0.07
    āji
    -0.07
    POSITIVE LOGITS
     habitudes
    0.09
     пользователя
    0.08
    习
    0.08
     behavioral
    0.08
    $user
    0.08
     desk
    0.08
    惯
    0.08
    เม
    0.08
     安
    0.08
    ویه
    0.07
    Act Density 0.006%

    No Known Activations