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

    Neuronpedia

    INDEX
    Explanations

    staff writer engineer sergeant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     servants
    0.48
     preh
    0.46
     viên
    0.41
     hitting
    0.40
     crew
    0.40
    人員
    0.40
     fetching
    0.40
     themselves
    0.40
     personnel
    0.40
     Crew
    0.39
    POSITIVE LOGITS
    writer
    0.45
    ann
    0.42
    include
    0.42
    our
    0.42
    дио
    0.42
    lng
    0.42
     scrivere
    0.42
    write
    0.41
    oluminescence
    0.40
    infection
    0.40
    Act Density 0.001%

    No Known Activations