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

    Neuronpedia

    INDEX
    Explanations

    con la

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     salaried
    0.41
     disillusioned
    0.41
     wrongdoing
    0.38
     कानून
    0.38
     unjust
    0.37
     unjustly
    0.37
     legitimacy
    0.36
     السياسي
    0.36
    权力
    0.36
     disgraceful
    0.36
    POSITIVE LOGITS
     or
    0.39
     ribbed
    0.35
    T
    0.35
     vegetable
    0.34
     gently
    0.34
    V
    0.34
     tube
    0.33
    wood
    0.33
     you
    0.33
     plastic
    0.33
    Act Density 2.081%

    No Known Activations