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

    Neuronpedia

    INDEX
    Explanations

    AI Agent, code, data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    manner
    0.30
    wilderness
    0.30
     cancer
    0.29
    cancer
    0.29
    mobility
    0.29
    <unused274>
    0.29
    <unused335>
    0.29
    agh
    0.28
    mirror
    0.28
    seal
    0.28
    POSITIVE LOGITS
    По
    0.32
     HttpResponse
    0.31
    До
    0.31
    Ди
    0.31
    ўцаў
    0.30
     Ejemplo
    0.30
    디
    0.30
     Ди
    0.29
     kotlin
    0.29
     Reglamento
    0.28
    Act Density 0.000%

    No Known Activations