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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     центра
    -0.07
     ارسال
    -0.07
    TRACT
    -0.06
     міс
    -0.06
     бать
    -0.06
     가지고
    -0.06
    _sim
    -0.06
    _VIS
    -0.06
    elden
    -0.05
    、新
    -0.05
    POSITIVE LOGITS
    ,node
    0.07
     (){↵
    0.07
    	Date
    0.06
     schema
    0.06
     Array
    0.06
    筆
    0.06
     they
    0.06
    |{↵
    0.06
     cotton
    0.06
     کردم
    0.06
    Act Density 0.000%

    No Known Activations