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

    Neuronpedia

    INDEX
    Explanations

    say "-"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thirds
    -0.07
    maps
    -0.07
    _extension
    -0.07
     euch
    -0.07
    (Room
    -0.07
    橱柜
    -0.07
     dresser
    -0.06
     rims
    -0.06
     rasp
    -0.06
    ,q
    -0.06
    POSITIVE LOGITS
    _non
    0.06
    䴖
    0.06
     gây
    0.06
    -delay
    0.06
    /apache
    0.06
    Você
    0.06
     Pt
    0.06
    ꪖ
    0.06
    _sub
    0.06
    𝑗
    0.06
    Act Density 0.006%

    No Known Activations