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

    Neuronpedia

    INDEX
    Explanations

    Y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invitation
    -0.07
    Confirmed
    -0.06
     Instructor
    -0.06
    ㅠㅠ
    -0.06
    Reviewed
    -0.06
    Kh
    -0.06
     Invasion
    -0.06
    ”。
    -0.06
    serialization
    -0.06
     yyn
    -0.06
    POSITIVE LOGITS
     (!!
    0.06
    èles
    0.06
     رسانه
    0.06
     infused
    0.06
    _uniform
    0.06
    _sep
    0.06
    (ll
    0.06
    алом
    0.06
    rose
    0.06
     etree
    0.06
    Act Density 0.009%

    No Known Activations