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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pecado
    -0.08
    宠
    -0.07
    ioq
    -0.07
     cuộc
    -0.07
     Tech
    -0.07
    ationen
    -0.07
     ఊ
    -0.07
     ओ
    -0.07
    odb
    -0.07
     Chef
    -0.07
    POSITIVE LOGITS
     separately
    0.13
     individually
    0.10
     afzonder
    0.09
     candidato
    0.09
     отдельно
    0.09
     각각
    0.09
     concurrently
    0.08
     independently
    0.08
     componentes
    0.08
    Candidates
    0.08
    Act Density 0.031%

    No Known Activations