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

    Neuronpedia

    INDEX
    Explanations

    air

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     better
    -0.07
    ບ
    -0.07
    itu
    -0.07
    оде
    -0.07
     preferred
    -0.07
    öz
    -0.07
    ờ
    -0.07
    inda
    -0.07
     điểm
    -0.07
    \Session
    -0.07
    POSITIVE LOGITS
     Conj
    0.08
    魔
    0.07
     project
    0.07
     transmit
    0.06
    最近
    0.06
    隐私
    0.06
    ивания
    0.06
     CAST
    0.06
     żyw
    0.06
    🕷
    0.06
    Act Density 0.004%

    No Known Activations