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

    Neuronpedia

    INDEX
    Explanations

    ),

    np_max-act · gemini-2.0-flash

    This neuron activates on version‐number tokens in API availability annotations (e.g. the “8.0,” “11.0,” etc., in API_AVAILABLE/API_UNAVAILABLE macros).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     accommodation
    -0.07
    Pipeline
    -0.06
     mer
    -0.06
    ")));↵↵
    -0.06
     ignored
    -0.06
     belt
    -0.06
    rf
    -0.06
     simulations
    -0.06
    安装
    -0.06
     recognize
    -0.06
    POSITIVE LOGITS
    (Me
    0.07
     colorWithRed
    0.07
    _imm
    0.07
    كن
    0.07
    (point
    0.06
     İç
    0.06
    iệng
    0.06
    oined
    0.06
    PullParser
    0.06
     iç
    0.06
    Act Density 0.001%

    No Known Activations