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

    Neuronpedia

    INDEX
    Explanations

    slot machines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    溵
    -0.07
    ราะ
    -0.07
    ℭ
    -0.07
    璥
    -0.07
    arena
    -0.07
     כלי
    -0.07
     niezbędn
    -0.07
    自主研发
    -0.07
    زا
    -0.07
    POSITIVE LOGITS
    ...")↵
    0.07
     post
    0.07
    公布了
    0.07
    Ï
    0.07
     verbose
    0.07
    })↵↵↵
    0.07
     ...↵↵↵↵
    0.07
     omission
    0.07
     "↵
    0.07
    "))↵↵
    0.07
    Act Density 0.003%

    No Known Activations