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

    Neuronpedia

    INDEX
    Explanations

    Sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ंभ
    -0.07
     sectarian
    -0.07
     �
    -0.07
    志
    -0.07
     Cristiano
    -0.07
     Cache
    -0.06
     Comments
    -0.06
     конферен
    -0.06
     Minor
    -0.06
    edores
    -0.06
    POSITIVE LOGITS
    *)↵
    0.07
    러
    0.06
    specs
    0.06
    _option
    0.06
    >X
    0.06
    MT
    0.06
    wj
    0.06
    GING
    0.06
    ][]
    0.06
     QFont
    0.06
    Act Density 0.003%

    No Known Activations