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

    Neuronpedia

    INDEX
    Explanations

    dates and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Currency
    0.43
    TRAS
    0.40
     disputed
    0.38
     Currency
    0.38
     townships
    0.38
     currency
    0.38
    Repe
    0.37
     Midland
    0.37
     verw
    0.37
     brake
    0.36
    POSITIVE LOGITS
    દાવાદ
    0.46
    শাহ
    0.38
     ਇਕ
    0.38
    𒊑
    0.38
    হাওয়া
    0.38
     女の子
    0.38
     Girlfriend
    0.37
    atinib
    0.37
    ニング
    0.36
     visualizations
    0.36
    Act Density 0.005%

    No Known Activations