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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (long
    -0.07
    ecome
    -0.06
    agt
    -0.06
    (double
    -0.06
    صور
    -0.06
    trag
    -0.06
    (pos
    -0.06
     loop
    -0.06
    legt
    -0.06
    rength
    -0.06
    POSITIVE LOGITS
     endors
    0.07
     春
    0.07
     »
    0.07
    聞
    0.07
     dernier
    0.06
    /plugins
    0.06
     debian
    0.06
    ?>">↵
    0.06
     focal
    0.06
    .Reflection
    0.06
    Act Density 0.015%

    No Known Activations