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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hai
    -0.07
     surtout
    -0.06
    альні
    -0.06
     plutôt
    -0.06
     Sul
    -0.06
    _pkt
    -0.06
    もり
    -0.06
     Amerik
    -0.06
     کنار
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    ۲۰۱
    0.07
    ,arr
    0.07
    .ensure
    0.07
     deprived
    0.07
    Ensure
    0.06
    Bundle
    0.06
    cj
    0.06
    ά
    0.06
     truths
    0.06
     config
    0.06
    Act Density 0.003%

    No Known Activations