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

    Neuronpedia

    INDEX
    Explanations

    ruin and disrupt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    整理
    0.36
     positioning
    0.35
    뻐
    0.35
    處
    0.34
     Adapt
    0.34
    ဆင့်
    0.34
     enable
    0.33
    梳
    0.33
     easier
    0.33
     Оси
    0.32
    POSITIVE LOGITS
     ruining
    1.27
     ruined
    1.15
     ruin
    1.12
     disrupts
    1.09
     detract
    1.06
     ruins
    1.05
     disrupting
    1.05
    玷
    1.02
     disrupted
    1.00
     disrupt
    0.99
    Act Density 0.021%

    No Known Activations