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

    Neuronpedia

    INDEX
    Explanations

    Input fields

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Registered
    -0.07
    PDF
    -0.07
    required
    -0.06
     Yah
    -0.06
     :-
    -0.06
    ीएस
    -0.06
    dato
    -0.06
     vz
    -0.06
    Assistant
    -0.06
    lastname
    -0.06
    POSITIVE LOGITS
     field
    0.07
    (pt
    0.07
    >'.↵
    0.07
    Ref
    0.06
     fields
    0.06
    ={!
    0.06
    чої
    0.06
     شي
    0.06
    ینه
    0.06
    ",'
    0.06
    Act Density 0.017%

    No Known Activations