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

    Neuronpedia

    INDEX
    Explanations

    pointers upwardsevaporate quicklypurchased within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ==-
    0.32
    ati
    0.31
     McMillan
    0.31
    ＜
    0.30
     Roberts
    0.30
    atii
    0.29
    keywords
    0.29
     Nelson
    0.29
     Richardson
    0.29
    usas
    0.29
    POSITIVE LOGITS
     milhões
    0.35
     metaverse
    0.35
    мену
    0.33
     vanes
    0.32
    𝒹
    0.32
    hiver
    0.31
     framework
    0.31
    韌
    0.31
     ду
    0.30
    𝙚
    0.30
    Act Density 0.001%

    No Known Activations