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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _argument
    -0.07
     Ded
    -0.07
     ||↵
    -0.07
    ,…↵↵
    -0.07
    ]];↵
    -0.07
     furry
    -0.07
     })↵↵
    -0.07
     ceremonial
    -0.06
     bravery
    -0.06
     quote
    -0.06
    POSITIVE LOGITS
     spear
    0.07
    ucz
    0.06
     kotlin
    0.06
    寺
    0.06
     Carr
    0.06
     सकत
    0.06
     Brett
    0.06
    ジ
    0.06
     secara
    0.06
     보고
    0.06
    Act Density 0.004%

    No Known Activations