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

    Neuronpedia

    INDEX
    Explanations

    daily, day

    np_max-act · gemini-2.0-flash

    The neuron is triggered by temporal frequency adverbs—most prominently the word “daily.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Shield
    -0.07
     صند
    -0.06
    _IList
    -0.06
     startup
    -0.06
     LDS
    -0.06
     nested
    -0.06
     ساخت
    -0.06
     Collider
    -0.06
    ίες
    -0.06
     مدل
    -0.06
    POSITIVE LOGITS
    都
    0.07
     '',↵
    0.07
    mill
    0.06
     tying
    0.06
     Б
    0.06
    .tpl
    0.06
     ramps
    0.06
    오
    0.06
     ['-
    0.06
    เขา
    0.06
    Act Density 0.016%

    No Known Activations