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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    潇
    -0.08
    펭
    -0.07
    作品内容
    -0.07
     אף
    -0.07
    合作伙伴
    -0.07
    ✕
    -0.07
    _CRYPTO
    -0.07
    ponential
    -0.07
    表态
    -0.07
    ------+
    -0.07
    POSITIVE LOGITS
    .articles
    0.07
    なくな
    0.07
    	account
    0.07
    (attribute
    0.06
     Sr
    0.06
     fat
    0.06
     pnl
    0.06
     UA
    0.06
     Nurses
    0.06
     hierarchy
    0.06
    Act Density 0.056%

    No Known Activations