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

    Neuronpedia

    INDEX
    Explanations

    integration completed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     don
    0.48
     didn
    0.46
     závod
    0.43
    rable
    0.43
    nému
    0.42
    స్తుంది
    0.42
    δά
    0.40
    ieurs
    0.40
    可以说
    0.40
    ônio
    0.39
    POSITIVE LOGITS
                    
    0.50
     popolare
    0.46
                             
    0.45
     fisica
    0.44
    と
    0.44
     popular
    0.43
     com
    0.42
                           
    0.42
     Popular
    0.42
     atract
    0.42
    Act Density 0.004%

    No Known Activations