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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    нее
    -0.07
    plevel
    -0.07
     planting
    -0.07
     kicking
    -0.07
     лечения
    -0.07
     benefited
    -0.06
     CEOs
    -0.06
    感谢
    -0.06
    exels
    -0.06
    POSITIVE LOGITS
     Pro
    0.08
    &lt
    0.07
    从中
    0.07
    tors
    0.07
    OLEAN
    0.07
    _diag
    0.07
    düğü
    0.07
     soothing
    0.07
     Construct
    0.07
     Sol
    0.07
    Act Density 0.002%

    No Known Activations