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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the word “the.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /ts
    -0.06
     ブ
    -0.06
    э
    -0.06
     economics
    -0.06
     screenshot
    -0.06
    	B
    -0.06
     sacrifices
    -0.06
    _phase
    -0.06
    .Tools
    -0.06
     bureaucracy
    -0.06
    POSITIVE LOGITS
    immer
    0.07
     Brick
    0.07
    _render
    0.07
     Asheville
    0.07
     retry
    0.06
    .Required
    0.06
    атки
    0.06
     fullest
    0.06
    :both
    0.06
    -for
    0.06
    Act Density 0.026%

    No Known Activations