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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thing
    -0.07
    lasses
    -0.07
     Behavior
    -0.06
    할
    -0.06
    icious
    -0.06
    แก
    -0.06
     managers
    -0.06
    ""
    -0.06
     Cody
    -0.06
    _family
    -0.06
    POSITIVE LOGITS
    ]])↵
    0.07
    '):
↵
    0.07
    ,)↵
    0.07
     làn
    0.07
    ('/')[-
    0.07
     มหาว
    0.06
    )}
↵
    0.06
     đ
    0.06
     المن
    0.06
    ]}↵
    0.06
    Act Density 0.045%

    No Known Activations