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

    Neuronpedia

    INDEX
    Explanations

    box set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дра
    -0.08
     potrze
    -0.08
    Prefs
    -0.07
    ﺪ
    -0.07
    /proto
    -0.06
     receivers
    -0.06
    >)↵
    -0.06
    Persistence
    -0.06
     Yönetim
    -0.06
    炉
    -0.06
    POSITIVE LOGITS
    �
    0.06
    ผม
    0.06
     attracted
    0.06
    received
    0.06
     occurs
    0.06
     Monitor
    0.06
    .onclick
    0.06
    columnName
    0.06
     Lottery
    0.06
     Casual
    0.06
    Act Density 0.012%

    No Known Activations