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

    Neuronpedia

    INDEX
    Explanations

    numbered list with bullets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …"
    0.48
    ▒
    0.46
    ¦
    0.46
    …,
    0.42
    kos
    0.42
    ellow
    0.40
    …?
    0.40
    …
    0.40
     déco
    0.39
     அனைவரும்
    0.38
    POSITIVE LOGITS
     Racial
    0.44
    㧕
    0.40
     Abstract
    0.38
     Deane
    0.37
     Ꭰ
    0.36
    룬
    0.35
    俪
    0.35
    戽
    0.35
    Ὁ
    0.35
     Glossary
    0.34
    Act Density 0.006%

    No Known Activations