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

    Neuronpedia

    INDEX
    Explanations

    say "the word the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     called
    -0.08
     efficient
    -0.08
    @Slf
    -0.07
    called
    -0.07
    Eff
    -0.07
    efficient
    -0.07
    }↵↵↵
    -0.07
    出来
    -0.07
    ’ou
    -0.07
    �্�
    -0.07
    POSITIVE LOGITS
    VIDEOS
    0.10
     Definition
    0.10
    定义
    0.10
    -definition
    0.10
     تعریف
    0.09
    _definition
    0.09
     Beschreibung
    0.09
     legales
    0.09
     정의
    0.09
     definido
    0.09
    Act Density 0.016%

    No Known Activations