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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chlorine
    -0.09
     неправ
    -0.08
    .Millisecond
    -0.08
     Chlor
    -0.08
     repudi
    -0.07
    şk
    -0.07
     nät
    -0.07
    houding
    -0.07
     vibr
    -0.07
    ould
    -0.07
    POSITIVE LOGITS
    able
    0.08
     Rankings
    0.08
     اظهار
    0.08
     checkbox
    0.08
     dataframe
    0.08
     Nachfrage
    0.08
     Checkbox
    0.08
    Wrapped
    0.08
     ラ
    0.08
     markdown
    0.08
    Act Density 0.007%

    No Known Activations