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

    Neuronpedia

    INDEX
    Explanations

    legal/political texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jorn
    -0.07
    Mis
    -0.07
     assistant
    -0.06
     gamma
    -0.06
    _ll
    -0.06
     Ocean
    -0.06
    riding
    -0.06
     LANGUAGE
    -0.06
     fores
    -0.06
    ريف
    -0.06
    POSITIVE LOGITS
     Pradesh
    0.07
     현재
    0.07
    Socket
    0.06
     cousins
    0.06
     Stamford
    0.06
    .Ptr
    0.06
    	auto
    0.06
     عبارت
    0.06
     Recently
    0.06
    IllegalArgumentException
    0.06
    Act Density 0.002%

    No Known Activations