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

    Neuronpedia

    INDEX
    Explanations

    double negative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caos
    0.35
    鹜
    0.35
    прочем
    0.35
    жать
    0.33
     observaciones
    0.33
     hablaremos
    0.33
    ocsát
    0.33
    panies
    0.33
    ᇂ
    0.32
    )。
    0.32
    POSITIVE LOGITS
     is
    0.44
     easy
    0.41
     durable
    0.40
     lightweight
    0.38
     was
    0.37
     reusable
    0.36
     sturdy
    0.36
     biodegradable
    0.35
     Durable
    0.35
     great
    0.35
    Act Density 0.000%

    No Known Activations