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

    Neuronpedia

    INDEX
    Explanations

    conflict of interest disclosure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    仵
    0.38
     Hunter
    0.37
     Bower
    0.37
     അക
    0.36
     Tul
    0.35
     بيت
    0.35
    気軽
    0.35
    striped
    0.35
     riff
    0.35
     Tu
    0.35
    POSITIVE LOGITS
     conflict
    1.04
     conflicts
    1.02
     conflicto
    0.96
    conflict
    0.96
     Conflicts
    0.95
     Conflict
    0.95
    Conflict
    0.91
     declared
    0.90
     konflik
    0.90
     conflictos
    0.90
    Act Density 0.001%

    No Known Activations