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

    Neuronpedia

    INDEX
    Explanations

    business logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idespread
    0.71
    రువు
    0.71
    Colorful
    0.65
    幇
    0.65
    দ্র
    0.64
    úncia
    0.63
    镀
    0.63
    Nonce
    0.62
     prist
    0.62
     guida
    0.62
    POSITIVE LOGITS
     logic
    4.98
     Logic
    4.43
    logic
    4.24
    逻辑
    4.24
    Logic
    4.23
     logical
    3.97
     lógica
    3.84
     logique
    3.77
    邏
    3.72
     logics
    3.71
    Act Density 0.873%

    No Known Activations