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

    Neuronpedia

    INDEX
    Explanations

    42

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yer
    -0.07
    	vector
    -0.07
     kop
    -0.06
    .endswith
    -0.06
     semaphore
    -0.06
     갤로그
    -0.06
     Tottenham
    -0.06
    .fixture
    -0.06
     fö
    -0.06
    .GetName
    -0.06
    POSITIVE LOGITS
    42
    0.08
    420
    0.08
     acoustic
    0.07
    epochs
    0.07
    672
    0.07
     {*
    0.07
    �
    0.07
     Riley
    0.07
    _tac
    0.06
     Ads
    0.06
    Act Density 0.027%

    No Known Activations