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

    Neuronpedia

    INDEX
    Explanations

    competing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	auth
    -0.08
     annotated
    -0.07
     Profiles
    -0.07
     Cart
    -0.07
    -extra
    -0.07
    汲取
    -0.07
    Must
    -0.07
     şimdi
    -0.06
    >'+
    -0.06
     Fortune
    -0.06
    POSITIVE LOGITS
    ocious
    0.07
    吼
    0.07
    换句话
    0.06
    웅
    0.06
    роме
    0.06
    _mx
    0.06
    会影响到
    0.06
    ongo
    0.06
    مقاومة
    0.06
     muscles
    0.06
    Act Density 0.038%

    No Known Activations