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

    Neuronpedia

    INDEX
    Explanations

    feedback loop alignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fact
    0.46
    brow
    0.42
    Bever
    0.42
    জগতের
    0.42
    Basel
    0.42
    haps
    0.41
    inherit
    0.41
    beh
    0.41
    anna
    0.40
    bea
    0.39
    POSITIVE LOGITS
     feedback
    1.15
     Feedback
    1.10
    Feedback
    1.06
     feedbacks
    1.02
    feedback
    0.94
     loop
    0.93
    反馈
    0.93
     loops
    0.89
     Loop
    0.79
     feeds
    0.77
    Act Density 0.007%

    No Known Activations