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

    Neuronpedia

    INDEX
    Explanations

    Foreign Languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	http
    -0.07
     Mom
    -0.06
    workflow
    -0.06
     annunci
    -0.06
    <()>
    -0.06
     UITableView
    -0.06
    (form
    -0.06
     salmon
    -0.06
     політи
    -0.06
    fahren
    -0.06
    POSITIVE LOGITS
     grap
    0.07
    ICC
    0.06
    П
    0.06
     chủ
    0.06
    Cannot
    0.06
     स
    0.06
     оди
    0.06
    ;base
    0.06
     нож
    0.06
     Wizards
    0.06
    Act Density 0.083%

    No Known Activations