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

    Neuronpedia

    INDEX
    Explanations

    equipment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     політи
    0.38
     राजनीतिक
    0.36
    ถาม
    0.34
    राजनी
    0.34
     brahm
    0.33
     hurtful
    0.32
     সংবিধান
    0.31
     السياسي
    0.31
     POLITICAL
    0.31
    玦
    0.31
    POSITIVE LOGITS
     In
    0.35
     L
    0.35
    ↵↵
    0.34
     R
    0.33
     forklift
    0.33
      
    0.33
     Cherry
    0.33
     Tractor
    0.33
     T
    0.32
     Industrial
    0.32
    Act Density 0.000%

    No Known Activations