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

    Neuronpedia

    INDEX
    Explanations

    scientific study

    np_max-act · gemini-2.0-flash

    The neuron fires on phrases citing earlier research or reports (e.g. “previous findings,” “other reports,” “these results support…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	NullCheck
    -0.06
     doch
    -0.06
    宽
    -0.06
    show
    -0.06
     řízení
    -0.06
    éfono
    -0.06
    ьте
    -0.06
    Hover
    -0.06
     UUID
    -0.06
     mối
    -0.06
    POSITIVE LOGITS
     Farm
    0.07
     vill
    0.07
    SCR
    0.07
    489
    0.07
    ooter
    0.07
    руз
    0.06
    px
    0.06
     मह
    0.06
    -proxy
    0.06
     Reasons
    0.06
    Act Density 0.013%

    No Known Activations