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

    Neuronpedia

    INDEX
    Explanations

    sue, lawsuit, damages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    น
    1.04
    is
    1.03
    el
    0.97
    ت
    0.89
    ক
    0.89
    in
    0.88
     homers
    0.88
    p
    0.88
    র
    0.88
    นี
    0.85
    POSITIVE LOGITS
     χρήση
    0.79
    き
    0.77
    valment
    0.74
     затем
    0.71
    pero
    0.71
     कोण
    0.71
    ö
    0.71
    <0x80>
    0.69
     θέση
    0.69
    欴
    0.68
    Act Density 0.000%

    No Known Activations