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

    Neuronpedia

    INDEX
    Explanations

    coding and deals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    0.17
    ،
    0.16
    ী
    0.16
     сприя
    0.15
     physiologically
    0.15
    ية
    0.14
     barrels
    0.14
     hydroxyl
    0.14
    、
    0.14
     больш
    0.14
    POSITIVE LOGITS
    0.24
    0.24
            
    0.23
        
    0.23
    0.21
    0.19
    ----------------
    0.19
    s
    0.19
    private
    0.19
                
    0.18
    Act Density 1.222%

    No Known Activations