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

    Neuronpedia

    INDEX
    Explanations

    Mixed random text snippets

    np_max-act · gemini-2.0-flash

    The neuron is keyed to references to specific days in a schedule (e.g. “Day 3,” “Day 4,” “Day 2,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -vis
    -0.07
    Au
    -0.06
     Ruby
    -0.06
     màu
    -0.06
     Boy
    -0.06
    ]],↵
    -0.06
    �
    -0.06
     Radio
    -0.06
    шили
    -0.06
     Unternehmen
    -0.06
    POSITIVE LOGITS
    _activ
    0.06
    	fields
    0.06
    啊
    0.06
     imprison
    0.06
    ��
    0.06
     내려
    0.06
     Vern
    0.06
    (amount
    0.06
    ENDER
    0.06
    ElementException
    0.06
    Act Density 0.231%

    No Known Activations