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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     broken
    -0.06
    ]}</
    -0.06
     historian
    -0.06
     Royal
    -0.06
     }}</
    -0.06
    Marshal
    -0.06
     benef
    -0.06
     outline
    -0.06
    .confirm
    -0.06
     repl
    -0.06
    POSITIVE LOGITS
    гар
    0.07
    -war
    0.06
    SOR
    0.06
    %',
    0.06
    朋
    0.06
     @$
    0.06
     diaper
    0.06
    dart
    0.06
     Lie
    0.06
    }/
    0.06
    Act Density 0.071%

    No Known Activations