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

    Neuronpedia

    INDEX
    Explanations

    Code/Scripts/Legal Text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="{{$
    -0.07
     CAUSED
    -0.07
    弋
    -0.07
    POL
    -0.06
     arttır
    -0.06
     zahl
    -0.06
     Sü
    -0.06
    sigma
    -0.06
    нути
    -0.06
     produto
    -0.06
    POSITIVE LOGITS
     From
    0.07
    λύ
    0.07
    انون
    0.06
     Marlins
    0.06
    achers
    0.06
    uctions
    0.06
    Für
    0.06
    /event
    0.06
    single
    0.06
     Basics
    0.06
    Act Density 0.000%

    No Known Activations