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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -acre
    -0.06
    clare
    -0.06
    ;↵↵↵
    -0.06
    aneously
    -0.06
     poles
    -0.06
    меш
    -0.06
     winnings
    -0.06
    盘
    -0.06
    _values
    -0.06
     différents
    -0.06
    POSITIVE LOGITS
    оятель
    0.07
     FH
    0.07
    /fs
    0.07
     Md
    0.07
    :bg
    0.06
     IPT
    0.06
     HttpStatus
    0.06
     Москва
    0.06
    　ｌ
    0.06
     Кам
    0.06
    Act Density 0.006%

    No Known Activations