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

    Neuronpedia

    INDEX
    Explanations

    entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пл
    -0.06
     Gol
    -0.06
     mobil
    -0.06
     gồm
    -0.06
    [input
    -0.06
    <My
    -0.06
    opens
    -0.06
    kul
    -0.06
    립
    -0.06
    maint
    -0.06
    POSITIVE LOGITS
    -metadata
    0.08
    Rep
    0.07
     shalt
    0.06
     klar
    0.06
    нання
    0.06
    earer
    0.06
     Equation
    0.06
     cookbook
    0.06
     Giving
    0.06
    OMBRE
    0.06
    Act Density 0.106%

    No Known Activations