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

    Neuronpedia

    INDEX
    Explanations

    typedef

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unab
    -0.07
    	ss
    -0.06
     ag
    -0.06
     المش
    -0.06
    adal
    -0.06
    _Rem
    -0.06
    shaw
    -0.06
    282
    -0.06
    masters
    -0.06
    肖
    -0.06
    POSITIVE LOGITS
     Bye
    0.07
     #-
    0.07
    Preferred
    0.07
    EH
    0.06
    examples
    0.06
    方式
    0.06
    _percentage
    0.06
     scrapped
    0.06
    Crypto
    0.06
    contact
    0.06
    Act Density 0.001%

    No Known Activations