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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     système
    -0.07
     isolation
    -0.06
     системи
    -0.06
     lanc
    -0.06
     ult
    -0.06
     تومان
    -0.06
    -Y
    -0.06
     dias
    -0.06
     runs
    -0.06
    کو
    -0.06
    POSITIVE LOGITS
     Serialization
    0.06
     paste
    0.06
    ImGui
    0.06
     than
    0.06
    OFFSET
    0.06
    StringLength
    0.06
     которую
    0.06
    none
    0.06
    through
    0.06
    Format
    0.06
    Act Density 0.002%

    No Known Activations