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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron detects column-name lists in SQL INSERT statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    、と
    -0.07
     ephem
    -0.06
    )")
    -0.06
    }`}
    -0.06
     منه
    -0.06
    ,q
    -0.06
     شاخه
    -0.06
    )f
    -0.06
    timezone
    -0.06
    Items
    -0.06
    POSITIVE LOGITS
    .Res
    0.08
    .↵
    0.08
    ibilidad
    0.07
    Lastly
    0.07
    alie
    0.07
    phalt
    0.06
    MFLOAT
    0.06
    .Struct
    0.06
    操作
    0.06
     Alexis
    0.06
    Act Density 0.007%

    No Known Activations