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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hp
    -0.09
    ".$
    -0.07
    vehicles
    -0.07
    '+
    -0.06
    (gui
    -0.06
     specs
    -0.06
     ld
    -0.06
    ipy
    -0.06
    لیسی
    -0.06
    ipated
    -0.06
    POSITIVE LOGITS
     [{'
    0.07
    anned
    0.06
     І
    0.06
    andra
    0.06
     fuel
    0.06
    اگر
    0.06
     itk
    0.06
     profoundly
    0.06
     ост
    0.06
    reation
    0.06
    Act Density 0.017%

    No Known Activations