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

    Neuronpedia

    INDEX
    Explanations

    Medicare

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    member
    -0.07
    Decoration
    -0.06
    pecific
    -0.06
    chedulers
    -0.06
     artikel
    -0.06
     Fucking
    -0.06
     getToken
    -0.06
     dicks
    -0.06
     Goddess
    -0.06
    具体
    -0.06
    POSITIVE LOGITS
    (xi
    0.07
     yell
    0.07
    (pd
    0.06
     proven
    0.06
    PL
    0.06
    749
    0.06
    电视
    0.06
    чем
    0.06
     Input
    0.06
    aus
    0.06
    Act Density 0.013%

    No Known Activations