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

    Neuronpedia

    INDEX
    Explanations

    violence, packs, payments, requested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    G
    0.75
    V
    0.64
    P
    0.55
    D
    0.55
    и
    0.55
    E
    0.53
    C
    0.52
    Little
    0.51
    hton
    0.49
    International
    0.49
    POSITIVE LOGITS
    膀
    0.47
    痞
    0.46
    各种
    0.45
     lésions
    0.45
     فونبټ
    0.44
     personer
    0.43
    >`;
    0.43
    :";
    0.43
    疟
    0.43
    伤害
    0.42
    Act Density 0.002%

    No Known Activations