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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IMessage
    -0.07
    Adobe
    -0.07
    ישה
    -0.07
    -0.07
    增大
    -0.07
    _micro
    -0.07
    相通
    -0.07
     mã
    -0.07
    ribbon
    -0.07
     Aluminium
    -0.07
    POSITIVE LOGITS
     transplant
    0.07
     Talk
    0.07
     unconstitutional
    0.07
     circle
    0.06
    ()][
    0.06
     Auckland
    0.06
     Total
    0.06
    <thead
    0.06
    }{↵
    0.06
     Or
    0.06
    Act Density 0.009%

    No Known Activations