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

    Neuronpedia

    INDEX
    Explanations

    Parentheses/brackets

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    siyon
    -0.07
    apgolly
    -0.07
    Shows
    -0.06
    .ComboBoxStyle
    -0.06
    (wx
    -0.06
    Neill
    -0.06
    TestCategory
    -0.06
     عالية
    -0.06
    _dense
    -0.06
     Kylie
    -0.06
    POSITIVE LOGITS
    ])),↵
    0.08
    '=>'
    0.07
    coord
    0.07
     })),↵
    0.07
    яб
    0.07
    );">↵
    0.07
     immigration
    0.07
     расстоя
    0.07
    .ToDouble
    0.06
    ]])
    0.06
    Act Density 0.009%

    No Known Activations