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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superhero
    -0.07
     OTP
    -0.07
    ób
    -0.07
     obec
    -0.07
     dü
    -0.06
     dok
    -0.06
     maken
    -0.06
     tostring
    -0.06
     바라
    -0.06
     leagues
    -0.06
    POSITIVE LOGITS
    .returnValue
    0.07
     Convenient
    0.06
    /runtime
    0.06
     Spect
    0.06
    려요
    0.06
    ,strong
    0.06
    CTIONS
    0.06
    _time
    0.06
     Leadership
    0.06
     undermine
    0.06
    Act Density 0.295%

    No Known Activations