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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    条件
    -0.07
     conscious
    -0.07
     blogger
    -0.07
     арми
    -0.06
    ERA
    -0.06
    conditions
    -0.06
     попыт
    -0.06
     Menu
    -0.06
     disputes
    -0.06
    上传
    -0.06
    POSITIVE LOGITS
    "]->
    0.07
     Lastly
    0.07
     =[
    0.07
    ếp
    0.07
    0.07
     )->
    0.07
     П
    0.07
    .Euler
    0.07
    ueblo
    0.06
    (Func
    0.06
    Act Density 0.024%

    No Known Activations