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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λλην
    -0.07
     JSGlobal
    -0.06
     f
    -0.06
     zipfile
    -0.06
     thần
    -0.06
     우
    -0.06
    蓝
    -0.06
    −
    -0.06
    шей
    -0.06
    -default
    -0.06
    POSITIVE LOGITS
    olia
    0.07
     Tarif
    0.07
    ализи
    0.06
     reviewed
    0.06
    opus
    0.06
    しており
    0.06
    .setBackground
    0.06
    __(*
    0.06
    شنبه
    0.06
    ोकर
    0.06
    Act Density 0.005%

    No Known Activations