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

    Neuronpedia

    INDEX
    Explanations

    agreements and discourse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    溫
    -0.08
    _TIMES
    -0.07
    绝
    -0.07
     apprentices
    -0.07
    "><
    -0.07
    有限公司
    -0.07
     cał
    -0.07
    辛
    -0.07
    <strong
    -0.07
     Savings
    -0.07
    POSITIVE LOGITS
     comic
    0.07
     pissed
    0.07
     yaptığı
    0.07
     заним
    0.06
    gorith
    0.06
    /python
    0.06
     inclus
    0.06
     birlik
    0.06
     děti
    0.06
     Ελλά
    0.06
    Act Density 0.529%

    No Known Activations