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
     прио
    0.38
     DOG
    0.37
    emission
    0.36
     Boring
    0.36
     هنوز
    0.36
     quán
    0.36
    빤
    0.35
    ForRow
    0.35
     Embar
    0.35
     rahat
    0.35
    POSITIVE LOGITS
    Conflict
    0.64
    Conflicts
    0.57
     conflict
    0.57
    冲突
    0.56
     Conflict
    0.54
     konflikt
    0.54
     conflicts
    0.54
     konflik
    0.52
    conflict
    0.50
     conflic
    0.50
    Act Density 0.049%

    No Known Activations