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

    Neuronpedia

    INDEX
    Explanations

    open

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of mechanical opening or closing actions (e.g., “open,” “close,” “opening,” “closing”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Latin
    -0.07
     Lana
    -0.07
    OLTIP
    -0.06
     ποι
    -0.06
     Latina
    -0.06
     Defined
    -0.06
     afterEach
    -0.06
     s
    -0.06
    latin
    -0.06
    ify
    -0.06
    POSITIVE LOGITS
     open
    0.07
     uç
    0.06
    打开
    0.06
     ké
    0.06
     RR
    0.06
     sequentially
    0.06
    双
    0.06
    rob
    0.06
    Gate
    0.06
    -open
    0.06
    Act Density 0.016%

    No Known Activations