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

    Neuronpedia

    INDEX
    Explanations

    instructions and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ESG
    0.54
     Governance
    0.53
     Federated
    0.53
    Governance
    0.53
     політи
    0.52
     revenue
    0.52
    Political
    0.51
    营收
    0.51
     Political
    0.50
    ნენ
    0.50
    POSITIVE LOGITS
     technique
    0.99
     Technique
    0.91
     técnica
    0.85
     moisture
    0.85
     TECHNI
    0.81
     rinsing
    0.76
     buttermilk
    0.76
     techniques
    0.75
     Humidity
    0.74
     moist
    0.73
    Act Density 0.049%

    No Known Activations