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

    Neuronpedia

    INDEX
    Explanations

    bias detection and mitigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    biology
    0.50
    ologically
    0.49
     bio
    0.49
     physicists
    0.49
    physics
    0.49
    bio
    0.48
    Bio
    0.47
    Physics
    0.47
     biology
    0.46
     physics
    0.45
    POSITIVE LOGITS
     Introdu
    0.47
    티
    0.41
    рів
    0.41
     定
    0.41
     introduit
    0.41
    вет
    0.41
    רי
    0.40
    引入
    0.40
     Einführung
    0.40
    减
    0.39
    Act Density 0.011%

    No Known Activations