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

    Neuronpedia

    INDEX
    Explanations

    contrasting conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ne
    -0.07
    矢
    -0.07
     involve
    -0.07
    À
    -0.07
    �
    -0.07
    ù
    -0.07
    .Y
    -0.07
    };
↵
↵
    -0.06
     onboard
    -0.06
     ya
    -0.06
    POSITIVE LOGITS
    招募
    0.08
    젬
    0.07
    _SOCKET
    0.07
    :".$
    0.07
     Locker
    0.07
     Continent
    0.06
    (Element
    0.06
    .term
    0.06
     '&'
    0.06
    动机
    0.06
    Act Density 0.025%

    No Known Activations