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

    Neuronpedia

    INDEX
    Explanations

    code and scripting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _app
    -0.07
     інститут
    -0.07
    ONES
    -0.07
     audience
    -0.07
    .notifications
    -0.07
     ru
    -0.07
    Train
    -0.06
    ۵۰
    -0.06
     trump
    -0.06
     imagine
    -0.06
    POSITIVE LOGITS
     faithful
    0.06
    entials
    0.06
    .:.:.:.:.:.:.:.:
    0.06
     polit
    0.06
     menacing
    0.06
     infertility
    0.06
     creampie
    0.06
     marvelous
    0.06
    gsub
    0.06
    ському
    0.06
    Act Density 0.071%

    No Known Activations