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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of people moving countries—i.e. “immigrated” or “emigrated” (often split across tokens) and the following “to [country]” phrase.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     stitch
    -0.07
    Control
    -0.07
    =!
    -0.06
     box
    -0.06
     anal
    -0.06
    _buffer
    -0.06
     cen
    -0.06
    Profile
    -0.06
     Пра
    -0.06
     понять
    -0.06
    POSITIVE LOGITS
     }↵↵
    0.07
     };↵↵
    0.06
     tempt
    0.06
    澳
    0.06
    รถ
    0.06
    	↵↵↵
    0.06
    })();↵↵
    0.06
    ght
    0.06
     ore
    0.06
     acceptable
    0.06
    Act Density 0.011%

    No Known Activations