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

    Neuronpedia

    INDEX
    Explanations

    conflict resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efficiency
    0.52
    骐
    0.50
    Efficiency
    0.47
     ዘዴ
    0.46
     Enzyme
    0.45
     Physiology
    0.45
     ইউনিভার
    0.45
     Reveal
    0.45
     Panic
    0.44
    муля
    0.44
    POSITIVE LOGITS
     conflict
    1.31
     conflicts
    1.25
    conflict
    1.20
     instability
    1.16
     violence
    1.13
     conflicto
    1.13
     konflikt
    1.13
     konflik
    1.11
     Konfl
    1.10
     conflictos
    1.09
    Act Density 0.026%

    No Known Activations