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

    Neuronpedia

    INDEX
    Explanations

    friend and friends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dut
    0.71
    вець
    0.71
     reine
    0.68
    тации
    0.67
     태
    0.67
     anchoring
    0.67
     payload
    0.67
     ultimatum
    0.67
    бенок
    0.65
    ペア
    0.65
    POSITIVE LOGITS
     friends
    3.83
     friend
    3.49
    friends
    3.21
     Friends
    3.19
    Friends
    3.17
    朋友
    3.03
     Friend
    2.96
    Friend
    2.93
     amigos
    2.92
    friend
    2.92
    Act Density 0.145%

    No Known Activations