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

    Neuronpedia

    INDEX
    Explanations

    Date and time code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FAX
    -0.08
    koop
    -0.08
     minced
    -0.08
    _mex
    -0.07
     mex
    -0.07
     flask
    -0.07
    Mex
    -0.07
     tomato
    -0.07
    tur
    -0.07
     econ
    -0.07
    POSITIVE LOGITS
     punctual
    0.12
     puntual
    0.09
    纪律
    0.08
     همچ
    0.08
     unquestionably
    0.08
    	bt
    0.08
     BT
    0.08
     bst
    0.08
     surprising
    0.07
     CET
    0.07
    Act Density 0.001%

    No Known Activations