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

    Neuronpedia

    INDEX
    Explanations

    caratter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Consider
    -0.07
     Proceedings
    -0.07
     Resource
    -0.07
    ▽
    -0.07
    (INVOKE
    -0.07
    ….↵↵
    -0.07
     virtue
    -0.07
    GameOver
    -0.06
     inspires
    -0.06
    -over
    -0.06
    POSITIVE LOGITS
     axs
    0.07
     curved
    0.07
    _cate
    0.07
     Brussels
    0.07
    Features
    0.07
    ,filename
    0.07
    的房子
    0.07
    .fetchall
    0.06
     paar
    0.06
    avirus
    0.06
    Act Density 0.006%

    No Known Activations