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

    Neuronpedia

    INDEX
    Explanations

    Ireland

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ⓔ
    -0.08
     sunset
    -0.07
     mood
    -0.07
    资源配置
    -0.06
     główn
    -0.06
    툰
    -0.06
    thon
    -0.06
    moon
    -0.06
     במקרה
    -0.06
     출력
    -0.06
    POSITIVE LOGITS
    ctor
    0.07
    �
    0.07
    Advertis
    0.07
    㮾
    0.06
    Models
    0.06
    首要
    0.06
     yab
    0.06
    都非常
    0.06
    	dst
    0.06
    sid
    0.06
    Act Density 0.004%

    No Known Activations