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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    こそ
    -0.06
     emphasize
    -0.06
    Spo
    -0.06
    -threat
    -0.06
     Motors
    -0.06
    AIR
    -0.06
    =(↵
    -0.06
    _OPTION
    -0.06
    古屋
    -0.06
     Discipline
    -0.06
    POSITIVE LOGITS
    PI
    0.06
    활동
    0.06
     respons
    0.06
     재
    0.06
    .correct
    0.06
     shootings
    0.06
     пак
    0.06
     договору
    0.06
    ικο
    0.05
    ậc
    0.05
    Act Density 0.051%

    No Known Activations