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

    Neuronpedia

    INDEX
    Explanations

    space launch or orbit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     מר
    0.41
    নী
    0.40
     lưới
    0.40
    処理
    0.39
    赃
    0.39
    Subset
    0.38
    Inbox
    0.38
     vaguely
    0.38
     UserService
    0.38
    ัต
    0.38
    POSITIVE LOGITS
    кер
    0.49
    ⸜
    0.49
    $-
    0.48
     logrado
    0.48
    XYGEN
    0.47
     ವರ್ಷ
    0.46
     diabet
    0.46
     sehr
    0.46
     personen
    0.46
    linien
    0.45
    Act Density 0.001%

    No Known Activations