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

    Neuronpedia

    INDEX
    Explanations

    late 2023/early 2024

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    はじめ
    0.52
     собы
    0.52
    TabPage
    0.52
    まり
    0.52
    ive
    0.50
     belladone
    0.50
     latéral
    0.50
    턴
    0.50
     Arbeits
    0.49
    ے
    0.48
    POSITIVE LOGITS
    yrs
    0.55
     tämän
    0.53
     birdies
    0.53
     этот
    0.51
    cargar
    0.51
     מה
    0.50
     OMG
    0.49
     Erin
    0.49
     Bhat
    0.49
     chickpeas
    0.48
    Act Density 0.009%

    No Known Activations