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 mathematical notation, especially LaTeX-style math delimiters and variable/formula tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cloth
    -0.07
    .Stream
    -0.06
    Sensor
    -0.06
    <Vector
    -0.06
    Cut
    -0.06
    Cancellation
    -0.06
     pet
    -0.06
     white
    -0.06
    -associated
    -0.06
    -hit
    -0.06
    POSITIVE LOGITS
    urb
    0.07
    >↵↵↵↵
    0.06
    iềm
    0.06
    .serv
    0.06
    ドラ
    0.06
    _nombre
    0.06
    _nome
    0.06
    	RuntimeObject
    0.06
     виробництва
    0.06
    eneral
    0.06
    Act Density 0.040%

    No Known Activations