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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    йн
    -0.07
    .gz
    -0.07
    泊
    -0.07
    (box
    -0.07
     exe
    -0.07
    ίου
    -0.06
    _cos
    -0.06
     oo
    -0.06
    _notify
    -0.06
     beberapa
    -0.06
    POSITIVE LOGITS
     Floyd
    0.07
    ployment
    0.07
     stability
    0.06
    heck
    0.06
    ЛА
    0.06
     false
    0.06
     City
    0.06
     Lucas
    0.06
     DateTime
    0.06
    	location
    0.06
    Act Density 0.000%

    No Known Activations