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

    Neuronpedia

    INDEX
    Explanations

    personal opinions, self-perception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ward
    -0.07
     Burr
    -0.07
     Costs
    -0.07
    褒
    -0.07
    _ARCHIVE
    -0.07
    ວ
    -0.06
    细化
    -0.06
    порт
    -0.06
     Senator
    -0.06
    	file
    -0.06
    POSITIVE LOGITS
    可信
    0.08
    第一
    0.07
     hatırl
    0.07
    帮
    0.07
    DMETHOD
    0.07
    真诚
    0.07
    mática
    0.06
    放下
    0.06
     amazingly
    0.06
    stdint
    0.06
    Act Density 0.189%

    No Known Activations