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

    Neuronpedia

    INDEX
    Explanations

    programming questions/discussions

    np_max-act · gemini-2.0-flash

    the neuron selectively detects participial verbs (gerunds or past‐participle forms) indicating ongoing or passive actions (e.g. “displaying,” “being,” “compiled”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     kiện
    -0.06
     Gron
    -0.06
    宣
    -0.06
    ordinated
    -0.06
    電影
    -0.06
    	box
    -0.06
     BAM
    -0.06
    하면서
    -0.06
    냥
    -0.06
     Terr
    -0.06
    POSITIVE LOGITS
    ">{
    0.07
    .Fat
    0.06
    .prevent
    0.06
     údajů
    0.06
    ');↵
    0.06
    ounters
    0.06
     supervisor
    0.06
     ACK
    0.06
    >window
    0.06
    ��
    0.06
    Act Density 0.056%

    No Known Activations