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

    Neuronpedia

    INDEX
    Explanations

    ill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mẽ
    -0.07
     swe
    -0.07
    Amb
    -0.06
    .firstname
    -0.06
     disadvantages
    -0.06
     culpa
    -0.06
     Successfully
    -0.06
     гост
    -0.06
     діяль
    -0.06
     fetisch
    -0.06
    POSITIVE LOGITS
     خرد
    0.07
    IBC
    0.07
    ylv
    0.06
    ũi
    0.06
     ΠΡ
    0.06
     getCategory
    0.06
    .setHorizontal
    0.06
     basename
    0.06
    UCKET
    0.06
    orpor
    0.06
    Act Density 0.000%

    No Known Activations