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

    Neuronpedia

    INDEX
    Explanations

    United States

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشين
    -0.59
     SqlCommand
    -0.54
     Amend
    -0.53
     Española
    -0.52
    הערות
    -0.52
     فريبيس
    -0.51
    gyz
    -0.51
     Anfitrión
    -0.50
     الحره
    -0.50
     اب
    -0.50
    POSITIVE LOGITS
     has
    0.60
    Портал
    0.60
     varies
    0.56
     raggiunto
    0.56
     traces
    0.56
     sees
    0.54
     relies
    0.54
     esternos
    0.53
     employs
    0.51
     reached
    0.50
    Act Density 0.004%

    No Known Activations