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

    Neuronpedia

    INDEX
    Explanations

    object

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getHost
    -0.07
     IDisposable
    -0.07
     devlet
    -0.07
    ेच
    -0.07
    ethod
    -0.06
    Article
    -0.06
    istik
    -0.06
    еви
    -0.06
    Nie
    -0.06
    University
    -0.06
    POSITIVE LOGITS
     ethnicity
    0.07
     (+
    0.07
    answer
    0.07
    =G
    0.07
     Guest
    0.06
     fChain
    0.06
    _marshaled
    0.06
    	tile
    0.06
     destination
    0.06
     �
    0.06
    Act Density 0.003%

    No Known Activations