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

    Neuronpedia

    INDEX
    Explanations

    °

    np_max-act · gemini-2.0-flash

    The neuron activates on the literal token “prompt,” i.e. it detects occurrences of the word “prompt.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    izzie
    -0.08
    ApplicationContext
    -0.07
    88
    -0.07
    alker
    -0.07
     dword
    -0.06
    ONEY
    -0.06
     servicio
    -0.06
    ubernetes
    -0.06
    ysql
    -0.06
    оку
    -0.06
    POSITIVE LOGITS
     disg
    0.07
     radial
    0.06
    @Autowired
    0.06
     resign
    0.06
     Medic
    0.06
    ková
    0.06
     Scrap
    0.06
     düğ
    0.06
    inject
    0.06
     Čech
    0.06
    Act Density 0.140%

    No Known Activations