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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on SQL query keywords and clause tokens (e.g. SELECT, FROM, WHERE, UPDATE, EXISTS).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fireplace
    -0.08
     SOUR
    -0.07
     krát
    -0.07
    .setSelection
    -0.07
     Aure
    -0.07
     روح
    -0.06
    Away
    -0.06
     DUP
    -0.06
    	Py
    -0.06
     Turks
    -0.06
    POSITIVE LOGITS
    配置
    0.07
     weigh
    0.07
    _INST
    0.06
    .jump
    0.06
    .Annotations
    0.06
    větší
    0.06
     strawberry
    0.06
    	inst
    0.06
     �
    0.06
     ye
    0.06
    Act Density 0.003%

    No Known Activations