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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash

    This neuron detects TypeScript type‐declaration keywords (e.g. “type,” “interface,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ("
    -0.07
    }`);↵
    -0.07
    Danger
    -0.06
    PreparedStatement
    -0.06
     Room
    -0.06
     kingdom
    -0.06
     Roses
    -0.06
    CURRENT
    -0.06
     ('
    -0.06
     End
    -0.06
    POSITIVE LOGITS
    _ble
    0.07
    滑
    0.06
    ToolBar
    0.06
     getSource
    0.06
    invert
    0.06
     dese
    0.06
    'aut
    0.06
     AE
    0.06
     Hezbollah
    0.06
    agma
    0.06
    Act Density 0.002%

    No Known Activations