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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash

    This neuron activates on ordinal step indicators (e.g. “first step in the … process”), marking the enumeration of procedural stages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _queries
    -0.07
    Pictures
    -0.06
     investors
    -0.06
     Latino
    -0.06
    ��
    -0.06
     accomplishments
    -0.06
     altogether
    -0.06
     dai
    -0.06
    える
    -0.06
    ]byte
    -0.06
    POSITIVE LOGITS
    speaker
    0.07
    adlo
    0.07
    	sound
    0.06
     TextFormField
    0.06
     gridBagConstraints
    0.06
     Tên
    0.06
     IICIII
    0.06
     egreg
    0.06
    tmp
    0.06
    ارج
    0.06
    Act Density 0.023%

    No Known Activations