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

    Neuronpedia

    INDEX
    Explanations

    Invisible Thread

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ParameterActive
    0.39
    onka
    0.38
     sétimo
    0.37
    mui
    0.36
     dipping
    0.36
    OPTV
    0.36
     dipolar
    0.36
     সপ্তম
    0.35
     डिप्ट
    0.35
    数值
    0.34
    POSITIVE LOGITS
     eas
    0.41
    πα
    0.39
    Gateway
    0.39
     Georgetown
    0.38
     اختی
    0.37
     सुरेंद्र
    0.37
    鹜
    0.36
     Jacques
    0.36
    द्री
    0.36
    inox
    0.36
    Act Density 0.000%

    No Known Activations