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

    Neuronpedia

    INDEX
    Explanations

    Code, programming

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     introduce
    -0.08
    一番
    -0.07
     filtered
    -0.07
    esium
    -0.07
     prend
    -0.07
     Whisper
    -0.07
    chair
    -0.07
     pien
    -0.07
    actic
    -0.07
    Starting
    -0.06
    POSITIVE LOGITS
    窝
    0.07
     COLUMN
    0.07
    .opts
    0.07
     catast
    0.07
     sufferers
    0.07
    @index
    0.07
     "**
    0.07
    IALIZED
    0.07
    微量元素
    0.06
    urse
    0.06
    Act Density 0.065%

    No Known Activations