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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝒎
    -0.07
     GENERIC
    -0.07
     örnek
    -0.07
    𝑨
    -0.07
    调试
    -0.07
    توقي
    -0.07
    节水
    -0.07
     конструк
    -0.07
    衅
    -0.06
     apartments
    -0.06
    POSITIVE LOGITS
    乖乖
    0.08
    走出
    0.08
    聽到
    0.07
    cache
    0.07
     Cbd
    0.07
    dot
    0.07
    하자
    0.07
     karşılaş
    0.07
     tribe
    0.07
    的认可
    0.06
    Act Density 0.010%

    No Known Activations