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

    Neuronpedia

    INDEX
    Explanations

    criticism, objections, controversy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Recovery
    0.46
    梳
    0.43
     Mỗi
    0.43
    Recovery
    0.42
     Boosting
    0.42
     synapse
    0.42
    移动
    0.41
    Mirror
    0.40
    整个
    0.40
     remaster
    0.40
    POSITIVE LOGITS
     objections
    1.18
     objection
    1.01
    反对
    1.01
     criticisms
    0.98
     protested
    0.96
     objecting
    0.95
     विरोध
    0.90
     criticism
    0.89
     protesting
    0.89
     opposition
    0.89
    Act Density 0.087%

    No Known Activations