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

    Neuronpedia

    INDEX
    Explanations

    improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SEAL
    -0.06
    олов
    -0.06
    िवस
    -0.06
    -book
    -0.06
    		 ↵
    -0.06
    ё
    -0.06
     setUp
    -0.06
    arrant
    -0.05
     ensemble
    -0.05
    Ser
    -0.05
    POSITIVE LOGITS
     importantes
    0.06
     electromagnetic
    0.06
    _ec
    0.06
    connecting
    0.06
     crisp
    0.06
     muschi
    0.06
     начинает
    0.06
    .Formatting
    0.06
    ufen
    0.06
     torino
    0.06
    Act Density 0.055%

    No Known Activations