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

    Neuronpedia

    INDEX
    Explanations

    Facebook

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     arch
    -0.07
     docs
    -0.06
     courtyard
    -0.06
    caller
    -0.06
    	long
    -0.06
     done
    -0.06
     repair
    -0.06
    柴纳
    -0.06
     cap
    -0.06
    POSITIVE LOGITS
    สม
    0.07
    alış
    0.07
    蚁
    0.06
    適用
    0.06
    ŭ
    0.06
     현
    0.06
    rzy
    0.06
     표
    0.06
    iza
    0.06
    _processes
    0.06
    Act Density 0.006%

    No Known Activations