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

    Neuronpedia

    INDEX
    Explanations

    Prime

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on SQL identifier tokens—particularly underscored column names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mechanics
    -0.07
    IFICATION
    -0.06
    Too
    -0.06
    isine
    -0.06
    ressive
    -0.06
     Fear
    -0.06
     persuasive
    -0.06
    .github
    -0.06
     optic
    -0.06
     timed
    -0.06
    POSITIVE LOGITS
    уль
    0.07
    _outline
    0.06
    Năm
    0.06
     VL
    0.06
     Phật
    0.06
    _CSS
    0.06
    _slide
    0.06
    _KEYWORD
    0.06
    ื้
    0.06
    _DISPLAY
    0.06
    Act Density 0.102%

    No Known Activations