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

    Neuronpedia

    INDEX
    Explanations

    island or islands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.70
    ()=>{
    1.52
    órios
    1.49
    टेगरी
    1.43
     wondered
    1.42
    ?}",
    1.40
     shortest
    1.35
    𝚔
    1.35
    一来
    1.30
    aS
    1.29
    POSITIVE LOGITS
    ित
    1.37
    ئی
    1.35
    для
    1.31
    ين
    1.28
    siehe
    1.26
    क
    1.23
    тельство
    1.22
    ام
    1.20
    ining
    1.19
    놈
    1.18
    Act Density 0.044%

    No Known Activations