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

    Neuronpedia

    INDEX
    Explanations

    /null

    np_max-act · gemini-2.0-flash

    The neuron detects shell redirection operations that send output (e.g. stdout or stderr) to “/dev/null.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ROOM
    -0.07
     Gy
    -0.07
    ﺪ
    -0.06
    CA
    -0.06
     آمده
    -0.06
     TBD
    -0.06
     XElement
    -0.06
    urnished
    -0.06
    <center
    -0.06
    &a
    -0.06
    POSITIVE LOGITS
    .Visual
    0.07
     nt
    0.06
    :utf
    0.06
    .setHeight
    0.06
     Wordpress
    0.06
     duy
    0.06
     nestled
    0.06
     PRIV
    0.06
    нят
    0.06
     verk
    0.06
    Act Density 0.001%

    No Known Activations