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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _socket
    -0.06
    +a
    -0.06
    Containers
    -0.06
    :I
    -0.06
    Execute
    -0.06
     позволя
    -0.06
     coordinating
    -0.06
     forbid
    -0.06
    kf
    -0.06
     вихов
    -0.06
    POSITIVE LOGITS
    Here
    0.07
    ,ep
    0.07
    Paragraph
    0.07
    ......
    0.07
     Faul
    0.07
     여기
    0.06
     inconsist
    0.06
    лаз
    0.06
    CUR
    0.06
    expire
    0.06
    Act Density 0.073%

    No Known Activations