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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     हिस
    -0.09
    イベント
    -0.09
    ablishment
    -0.08
    竟
    -0.08
    critical
    -0.08
    :absolute
    -0.08
    大片
    -0.08
     Hoop
    -0.08
    .Tx
    -0.08
     Duplex
    -0.08
    POSITIVE LOGITS
     принадлеж
    0.10
     официаль
    0.09
    GPT
    0.09
     GPT
    0.09
     оз
    0.08
     روب
    0.08
     концеп
    0.08
    我是
    0.08
     моей
    0.08
     предназнач
    0.08
    Act Density 0.157%

    No Known Activations