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 activates on temporal sequencing words (e.g. “after,” “subsequently,” “later,” “following”) indicating shifts in time.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    applicant
    -0.07
     kiếm
    -0.07
    YELLOW
    -0.07
    _UNSUPPORTED
    -0.07
     chicas
    -0.07
     geek
    -0.07
     meer
    -0.07
    _tracker
    -0.07
     artwork
    -0.07
     /><
    -0.06
    POSITIVE LOGITS
     afterwards
    0.07
    vl
    0.06
    ･
    0.06
    B
    0.06
     permitted
    0.06
    _txn
    0.06
    Cos
    0.06
    After
    0.06
     이후
    0.06
     giờ
    0.06
    Act Density 0.034%

    No Known Activations