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

    Neuronpedia

    INDEX
    Explanations

    _le

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adu
    -0.06
    ungi
    -0.06
    tic
    -0.06
    getY
    -0.06
     cabbage
    -0.06
    	yy
    -0.06
    pathname
    -0.06
    urope
    -0.06
    ым
    -0.06
    -ticket
    -0.06
    POSITIVE LOGITS
    بع
    0.07
     Globe
    0.07
    协
    0.06
    """↵↵
    0.06
    _conversion
    0.06
     privileged
    0.06
    (":
    0.06
     ditch
    0.06
     Credentials
    0.06
     når
    0.06
    Act Density 0.001%

    No Known Activations