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
     copyrights
    -0.07
    tutorial
    -0.07
     Khi
    -0.07
     오
    -0.07
     osg
    -0.07
    itu
    -0.06
    ็อก
    -0.06
     artır
    -0.06
     Suit
    -0.06
    -pres
    -0.06
    POSITIVE LOGITS
    CharacterSet
    0.07
    .Flush
    0.06
     Want
    0.06
    agus
    0.06
     '@/
    0.06
    @dynamic
    0.06
     unconstitutional
    0.06
    iners
    0.06
    prompt
    0.06
    <GameObject
    0.06
    Act Density 0.133%

    No Known Activations