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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of integer variable declarations, especially the variable “x.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    аров
    -0.07
    sterdam
    -0.07
    Pets
    -0.06
    oll
    -0.06
     screamed
    -0.06
    llum
    -0.06
    ventory
    -0.06
    rief
    -0.06
     musician
    -0.06
    alsex
    -0.06
    POSITIVE LOGITS
     věc
    0.07
     wicht
    0.07
     것이다
    0.07
    					↵					↵
    0.07
    					↵
    0.07
                      ↵
    0.07
           
    0.07
    			↵
    0.06
     пат
    0.06
               
    0.06
    Act Density 0.080%

    No Known Activations