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

    Neuronpedia

    INDEX
    Explanations

    apples and fruits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Beasts
    1.67
     Được
    1.61
     lemmas
    1.45
    us
    1.45
    ஔ
    1.45
    Бы
    1.38
     literals
    1.37
    emails
    1.37
     Beast
    1.35
     matchups
    1.35
    POSITIVE LOGITS
    maları
    1.48
    리
    1.47
     remedied
    1.45
    am
    1.44
     apples
    1.44
    lardan
    1.44
    ラ
    1.40
    vação
    1.39
     cider
    1.37
    ことにより
    1.37
    Act Density 0.009%

    No Known Activations