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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the word “characterization,” i.e. it detects when an abstract reports the characterization of a material or compound.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Graz
    -0.07
     develops
    -0.07
    _epi
    -0.07
     histogram
    -0.07
     Mahmoud
    -0.07
    ornings
    -0.06
    AMESPACE
    -0.06
    Evento
    -0.06
    olen
    -0.06
     следующ
    -0.06
    POSITIVE LOGITS
    Ess
    0.07
     نظر
    0.06
    Form
    0.06
    .phi
    0.06
    _wr
    0.06
    qa
    0.05
    ，“
    0.05
    =/
    0.05
    iterator
    0.05
    =log
    0.05
    Act Density 0.025%

    No Known Activations