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

    Neuronpedia

    INDEX
    Explanations

    choices, lists, and questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     canh
    -0.06
    α
    -0.06
     Cuomo
    -0.06
    ecies
    -0.06
    _profile
    -0.06
    upa
    -0.06
    也
    -0.06
     catch
    -0.05
    _CE
    -0.05
    退出
    -0.05
    POSITIVE LOGITS
    Questions
    0.07
     isol
    0.07
     иму
    0.06
     compuls
    0.06
     onward
    0.06
     loadData
    0.06
     sexkontakte
    0.06
    醒
    0.06
     Disp
    0.06
     tied
    0.06
    Act Density 0.032%

    No Known Activations