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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     фон
    -0.07
    劳
    -0.07
    累
    -0.06
     gather
    -0.06
    _APPRO
    -0.06
     wonder
    -0.06
    _POP
    -0.06
    홍
    -0.06
    Requires
    -0.06
    ,target
    -0.06
    POSITIVE LOGITS
    "/>
↵
    0.07
    我去
    0.07
     كانوا
    0.07
    "،
    0.07
    .parts
    0.07
    }";↵
    0.07
    Maker
    0.07
    0.06
    )[:
    0.06
    મ
    0.06
    Act Density 0.032%

    No Known Activations