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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NZ
    -0.07
    orney
    -0.07
    oux
    -0.07
    cribing
    -0.07
     Lexus
    -0.07
    inea
    -0.07
    整改
    -0.06
    山县
    -0.06
    ruptcy
    -0.06
    conomy
    -0.06
    POSITIVE LOGITS
     Eva
    0.07
    投行
    0.06
    沈
    0.06
    .nlm
    0.06
    На
    0.06
    בעיות
    0.06
    网民
    0.06
     yytype
    0.06
     underlying
    0.06
    "}↵
    0.06
    Act Density 0.289%

    No Known Activations