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

    Neuronpedia

    INDEX
    Explanations

    bias mitigation and detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.21
    sl
    0.99
    site
    0.98
    su
    0.97
    service
    0.94
    send
    0.93
    h
    0.92
    tag
    0.89
    <h4>
    0.88
    ts
    0.88
    POSITIVE LOGITS
    ↵↵
    1.09
     bias
    0.99
     biases
    0.92
    ри
    0.89
    he
    0.88
     thiab
    0.87
     biased
    0.87
     clínicos
    0.87
     và
    0.86
     biais
    0.86
    Act Density 0.010%

    No Known Activations