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

    Neuronpedia

    INDEX
    Explanations

    conflict and disputes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rivals
    0.51
     fél
    0.43
     Dresses
    0.42
    ప్రత్యర్థి
    0.41
     samtid
    0.41
    Attk
    0.41
    elu
    0.40
    Crawler
    0.39
     Quattro
    0.39
     ፈ
    0.39
    POSITIVE LOGITS
    Conflicts
    0.76
     conflict
    0.76
     conflicts
    0.75
     Conflicts
    0.71
    冲突
    0.70
     Konfl
    0.70
     Conflict
    0.70
    conflict
    0.68
     konflik
    0.68
     clash
    0.67
    Act Density 0.000%

    No Known Activations