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

    Neuronpedia

    INDEX
    Explanations

    university of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hém
    1.00
     números
    0.99
     memória
    0.92
     défin
    0.92
     vídeos
    0.91
     níveis
    0.90
     índices
    0.89
     família
    0.89
     configuración
    0.89
     térm
    0.89
    POSITIVE LOGITS
     University
    1.29
    )
    1.17
    '
    1.16
    >
    1.16
    .
    1.14
    -
    1.14
    University
    1.12
     universities
    1.07
    0
    1.07
     Universities
    1.06
    Act Density 0.022%

    No Known Activations