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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     +"
    -0.08
    طفال
    -0.07
     Pay
    -0.07
     Shia
    -0.07
     теб
    -0.06
     хвор
    -0.06
     Plant
    -0.06
    _DOM
    -0.06
     ;;^
    -0.06
    .datasets
    -0.06
    POSITIVE LOGITS
    idea
    0.06
     activeClassName
    0.06
    qua
    0.06
     exporters
    0.06
    holder
    0.06
    ुप
    0.06
     melody
    0.06
    クション
    0.06
    portun
    0.06
    stuff
    0.06
    Act Density 0.002%

    No Known Activations