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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cmp
    -0.07
    UDGE
    -0.07
     QU
    -0.07
    .com
    -0.07
     geldi
    -0.07
     CPU
    -0.07
    363
    -0.07
     Helen
    -0.07
     Howe
    -0.07
     themes
    -0.07
    POSITIVE LOGITS
     discretionary
    0.06
    ()).
    0.06
     Pier
    0.06
     })}↵
    0.06
     contribute
    0.06
     letting
    0.06
    "]);
    0.06
    )'],↵
    0.06
    vest
    0.06
    �
    0.06
    Act Density 0.043%

    No Known Activations