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

    Neuronpedia

    INDEX
    Explanations

    legal filings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exter
    -0.07
    lineEdit
    -0.07
    乙
    -0.06
    464
    -0.06
    <"
    -0.06
    iyoruz
    -0.06
    坪
    -0.06
    imizin
    -0.06
    まる
    -0.06
     DEL
    -0.06
    POSITIVE LOGITS
     how
    0.07
     arrival
    0.06
     wished
    0.06
     nonlinear
    0.06
     advising
    0.06
    Listener
    0.06
     certificate
    0.06
    addresses
    0.06
     therapists
    0.06
     sens
    0.06
    Act Density 0.009%

    No Known Activations