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

    Neuronpedia

    INDEX
    Explanations

    smartwatches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仗
    -0.07
     neglected
    -0.07
    achelor
    -0.07
    اعد
    -0.07
    讨厌
    -0.06
     conjug
    -0.06
    佩服
    -0.06
    حق
    -0.06
    ميل
    -0.06
    偏离
    -0.06
    POSITIVE LOGITS
     !$
    0.07
    �
    0.07
    Collections
    0.07
    .inventory
    0.07
     statuses
    0.07
    球场
    0.07
    ㈰
    0.06
     (...)
    0.06
     koş
    0.06
    ♉
    0.06
    Act Density 0.013%

    No Known Activations