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

    Neuronpedia

    INDEX
    Explanations

    technology and human interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (and
    -0.07
    apas
    -0.07
    MODE
    -0.06
    床
    -0.06
    鸡
    -0.06
     如果
    -0.06
     badge
    -0.06
    しょう
    -0.06
    	case
    -0.06
    、二
    -0.06
    POSITIVE LOGITS
     entreprene
    0.07
    bohydr
    0.06
     Artikel
    0.06
    (library
    0.06
    eriod
    0.06
    borne
    0.06
    *);↵
    0.06
    .middle
    0.06
    kerja
    0.06
    �
    0.06
    Act Density 0.146%

    No Known Activations