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

    Neuronpedia

    INDEX
    Explanations

    exploitation and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synchronous
    0.83
    लांग
    0.75
     synchronized
    0.72
    同步
    0.72
     convulsions
    0.70
     declared
    0.69
     prohib
    0.68
     prohibitions
    0.67
     prohibited
    0.66
     जुगा
    0.65
    POSITIVE LOGITS
     exploitation
    2.03
     exploited
    1.80
     explo
    1.78
    exploitation
    1.67
     cheated
    1.64
     exploit
    1.63
     betrayal
    1.62
     Explo
    1.60
     betrayed
    1.54
     exploiting
    1.51
    Act Density 0.292%

    No Known Activations